From 9d3427490a7427a855d62dc8565c92880743e5a6 Mon Sep 17 00:00:00 2001 From: Jimmy Lin Date: Tue, 21 Nov 2023 06:32:02 -0500 Subject: [PATCH] Clean up of HNSW indexing code (#2265) + Refactored and cleaned up HNSH indexing code + Cleaned up logging in test cases (less verbose) + Renamed args topicfield to topicField, topicreader to topicReader + Renamed LuceneDenseVectorDocumentGenerator to HnswDenseVectorDocumentGenerator for consistency --- .../regressions-backgroundlinking18.md | 8 +- .../regressions-backgroundlinking19.md | 8 +- .../regressions-backgroundlinking20.md | 8 +- ...regressions-beir-v1.0.0-arguana-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-arguana-flat.md | 4 +- ...ressions-beir-v1.0.0-arguana-multifield.md | 4 +- ...arguana-splade-distil-cocodenser-medium.md | 4 +- ...sions-beir-v1.0.0-arguana-unicoil-noexp.md | 4 +- .../regressions-beir-v1.0.0-bioasq-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-bioasq-flat.md | 4 +- ...gressions-beir-v1.0.0-bioasq-multifield.md | 4 +- ...-bioasq-splade-distil-cocodenser-medium.md | 4 +- ...ssions-beir-v1.0.0-bioasq-unicoil-noexp.md | 4 +- ...sions-beir-v1.0.0-climate-fever-flat-wp.md | 4 +- ...ressions-beir-v1.0.0-climate-fever-flat.md | 4 +- ...ns-beir-v1.0.0-climate-fever-multifield.md | 4 +- ...e-fever-splade-distil-cocodenser-medium.md | 4 +- ...beir-v1.0.0-climate-fever-unicoil-noexp.md | 4 +- ...beir-v1.0.0-cqadupstack-android-flat-wp.md | 4 +- ...ns-beir-v1.0.0-cqadupstack-android-flat.md | 4 +- ...r-v1.0.0-cqadupstack-android-multifield.md | 4 +- ...android-splade-distil-cocodenser-medium.md | 4 +- ...1.0.0-cqadupstack-android-unicoil-noexp.md | 4 +- ...beir-v1.0.0-cqadupstack-english-flat-wp.md | 4 +- ...ns-beir-v1.0.0-cqadupstack-english-flat.md | 4 +- ...r-v1.0.0-cqadupstack-english-multifield.md | 4 +- ...english-splade-distil-cocodenser-medium.md | 4 +- ...1.0.0-cqadupstack-english-unicoil-noexp.md | 4 +- ...-beir-v1.0.0-cqadupstack-gaming-flat-wp.md | 4 +- ...ons-beir-v1.0.0-cqadupstack-gaming-flat.md | 4 +- ...ir-v1.0.0-cqadupstack-gaming-multifield.md | 4 +- ...-gaming-splade-distil-cocodenser-medium.md | 4 +- ...v1.0.0-cqadupstack-gaming-unicoil-noexp.md | 4 +- ...ons-beir-v1.0.0-cqadupstack-gis-flat-wp.md | 4 +- ...ssions-beir-v1.0.0-cqadupstack-gis-flat.md | 4 +- ...-beir-v1.0.0-cqadupstack-gis-multifield.md | 4 +- ...ack-gis-splade-distil-cocodenser-medium.md | 4 +- ...ir-v1.0.0-cqadupstack-gis-unicoil-noexp.md | 4 +- ...-v1.0.0-cqadupstack-mathematica-flat-wp.md | 4 +- ...eir-v1.0.0-cqadupstack-mathematica-flat.md | 4 +- ....0.0-cqadupstack-mathematica-multifield.md | 4 +- ...ematica-splade-distil-cocodenser-medium.md | 4 +- ...0-cqadupstack-mathematica-unicoil-noexp.md | 4 +- ...beir-v1.0.0-cqadupstack-physics-flat-wp.md | 4 +- ...ns-beir-v1.0.0-cqadupstack-physics-flat.md | 4 +- ...r-v1.0.0-cqadupstack-physics-multifield.md | 4 +- ...physics-splade-distil-cocodenser-medium.md | 4 +- ...1.0.0-cqadupstack-physics-unicoil-noexp.md | 4 +- ...-v1.0.0-cqadupstack-programmers-flat-wp.md | 4 +- ...eir-v1.0.0-cqadupstack-programmers-flat.md | 4 +- ....0.0-cqadupstack-programmers-multifield.md | 4 +- ...rammers-splade-distil-cocodenser-medium.md | 4 +- ...0-cqadupstack-programmers-unicoil-noexp.md | 4 +- ...s-beir-v1.0.0-cqadupstack-stats-flat-wp.md | 4 +- ...ions-beir-v1.0.0-cqadupstack-stats-flat.md | 4 +- ...eir-v1.0.0-cqadupstack-stats-multifield.md | 4 +- ...k-stats-splade-distil-cocodenser-medium.md | 4 +- ...-v1.0.0-cqadupstack-stats-unicoil-noexp.md | 4 +- ...ons-beir-v1.0.0-cqadupstack-tex-flat-wp.md | 4 +- ...ssions-beir-v1.0.0-cqadupstack-tex-flat.md | 4 +- ...-beir-v1.0.0-cqadupstack-tex-multifield.md | 4 +- ...ack-tex-splade-distil-cocodenser-medium.md | 4 +- ...ir-v1.0.0-cqadupstack-tex-unicoil-noexp.md | 4 +- ...ns-beir-v1.0.0-cqadupstack-unix-flat-wp.md | 4 +- ...sions-beir-v1.0.0-cqadupstack-unix-flat.md | 4 +- ...beir-v1.0.0-cqadupstack-unix-multifield.md | 4 +- ...ck-unix-splade-distil-cocodenser-medium.md | 4 +- ...r-v1.0.0-cqadupstack-unix-unicoil-noexp.md | 4 +- ...r-v1.0.0-cqadupstack-webmasters-flat-wp.md | 4 +- ...beir-v1.0.0-cqadupstack-webmasters-flat.md | 4 +- ...1.0.0-cqadupstack-webmasters-multifield.md | 4 +- ...masters-splade-distil-cocodenser-medium.md | 4 +- ....0-cqadupstack-webmasters-unicoil-noexp.md | 4 +- ...ir-v1.0.0-cqadupstack-wordpress-flat-wp.md | 4 +- ...-beir-v1.0.0-cqadupstack-wordpress-flat.md | 4 +- ...v1.0.0-cqadupstack-wordpress-multifield.md | 4 +- ...rdpress-splade-distil-cocodenser-medium.md | 4 +- ...0.0-cqadupstack-wordpress-unicoil-noexp.md | 4 +- ...ions-beir-v1.0.0-dbpedia-entity-flat-wp.md | 4 +- ...essions-beir-v1.0.0-dbpedia-entity-flat.md | 4 +- ...s-beir-v1.0.0-dbpedia-entity-multifield.md | 4 +- ...-entity-splade-distil-cocodenser-medium.md | 4 +- ...eir-v1.0.0-dbpedia-entity-unicoil-noexp.md | 4 +- .../regressions-beir-v1.0.0-fever-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-fever-flat.md | 4 +- ...egressions-beir-v1.0.0-fever-multifield.md | 4 +- ...0-fever-splade-distil-cocodenser-medium.md | 4 +- ...essions-beir-v1.0.0-fever-unicoil-noexp.md | 4 +- .../regressions-beir-v1.0.0-fiqa-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-fiqa-flat.md | 4 +- ...regressions-beir-v1.0.0-fiqa-multifield.md | 4 +- ....0-fiqa-splade-distil-cocodenser-medium.md | 4 +- ...ressions-beir-v1.0.0-fiqa-unicoil-noexp.md | 4 +- ...egressions-beir-v1.0.0-hotpotqa-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-hotpotqa-flat.md | 4 +- ...essions-beir-v1.0.0-hotpotqa-multifield.md | 4 +- ...otpotqa-splade-distil-cocodenser-medium.md | 4 +- ...ions-beir-v1.0.0-hotpotqa-unicoil-noexp.md | 4 +- ...egressions-beir-v1.0.0-nfcorpus-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-nfcorpus-flat.md | 4 +- ...essions-beir-v1.0.0-nfcorpus-multifield.md | 4 +- ...fcorpus-splade-distil-cocodenser-medium.md | 4 +- ...ions-beir-v1.0.0-nfcorpus-unicoil-noexp.md | 4 +- .../regressions-beir-v1.0.0-nq-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-nq-flat.md | 4 +- .../regressions-beir-v1.0.0-nq-multifield.md | 4 +- ....0.0-nq-splade-distil-cocodenser-medium.md | 4 +- ...egressions-beir-v1.0.0-nq-unicoil-noexp.md | 4 +- .../regressions-beir-v1.0.0-quora-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-quora-flat.md | 4 +- ...egressions-beir-v1.0.0-quora-multifield.md | 4 +- ...0-quora-splade-distil-cocodenser-medium.md | 4 +- ...essions-beir-v1.0.0-quora-unicoil-noexp.md | 4 +- ...egressions-beir-v1.0.0-robust04-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-robust04-flat.md | 4 +- ...essions-beir-v1.0.0-robust04-multifield.md | 4 +- ...obust04-splade-distil-cocodenser-medium.md | 4 +- ...ions-beir-v1.0.0-robust04-unicoil-noexp.md | 4 +- ...regressions-beir-v1.0.0-scidocs-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-scidocs-flat.md | 4 +- ...ressions-beir-v1.0.0-scidocs-multifield.md | 4 +- ...scidocs-splade-distil-cocodenser-medium.md | 4 +- ...sions-beir-v1.0.0-scidocs-unicoil-noexp.md | 4 +- ...regressions-beir-v1.0.0-scifact-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-scifact-flat.md | 4 +- ...ressions-beir-v1.0.0-scifact-multifield.md | 4 +- ...scifact-splade-distil-cocodenser-medium.md | 4 +- ...sions-beir-v1.0.0-scifact-unicoil-noexp.md | 4 +- ...egressions-beir-v1.0.0-signal1m-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-signal1m-flat.md | 4 +- ...essions-beir-v1.0.0-signal1m-multifield.md | 4 +- ...ignal1m-splade-distil-cocodenser-medium.md | 4 +- ...ions-beir-v1.0.0-signal1m-unicoil-noexp.md | 4 +- ...ressions-beir-v1.0.0-trec-covid-flat-wp.md | 4 +- ...regressions-beir-v1.0.0-trec-covid-flat.md | 4 +- ...sions-beir-v1.0.0-trec-covid-multifield.md | 4 +- ...c-covid-splade-distil-cocodenser-medium.md | 4 +- ...ns-beir-v1.0.0-trec-covid-unicoil-noexp.md | 4 +- ...gressions-beir-v1.0.0-trec-news-flat-wp.md | 4 +- .../regressions-beir-v1.0.0-trec-news-flat.md | 4 +- ...ssions-beir-v1.0.0-trec-news-multifield.md | 4 +- ...ec-news-splade-distil-cocodenser-medium.md | 4 +- ...ons-beir-v1.0.0-trec-news-unicoil-noexp.md | 4 +- ...ns-beir-v1.0.0-webis-touche2020-flat-wp.md | 4 +- ...sions-beir-v1.0.0-webis-touche2020-flat.md | 4 +- ...beir-v1.0.0-webis-touche2020-multifield.md | 4 +- ...che2020-splade-distil-cocodenser-medium.md | 4 +- ...r-v1.0.0-webis-touche2020-unicoil-noexp.md | 4 +- docs/regressions/regressions-car17v1.5.md | 14 +- .../regressions-car17v2.0-doc2query.md | 14 +- docs/regressions/regressions-car17v2.0.md | 14 +- docs/regressions/regressions-ciral-v1.0-ha.md | 4 +- docs/regressions/regressions-ciral-v1.0-so.md | 4 +- docs/regressions/regressions-ciral-v1.0-sw.md | 4 +- docs/regressions/regressions-ciral-v1.0-yo.md | 4 +- docs/regressions/regressions-clef06-fr.md | 4 +- docs/regressions/regressions-core17.md | 14 +- docs/regressions/regressions-core18.md | 14 +- docs/regressions/regressions-cw09b.md | 38 +-- docs/regressions/regressions-cw12.md | 18 +- docs/regressions/regressions-cw12b13.md | 26 +- docs/regressions/regressions-disk12.md | 38 +-- docs/regressions/regressions-disk45.md | 62 ++-- docs/regressions/regressions-dl19-doc-ca.md | 4 +- .../regressions-dl19-doc-docTTTTTquery.md | 14 +- .../regressions-dl19-doc-hgf-wp.md | 4 +- .../regressions-dl19-doc-segmented-ca.md | 4 +- ...ssions-dl19-doc-segmented-docTTTTTquery.md | 14 +- ...ssions-dl19-doc-segmented-unicoil-noexp.md | 8 +- .../regressions-dl19-doc-segmented-unicoil.md | 8 +- .../regressions-dl19-doc-segmented-wp.md | 4 +- .../regressions-dl19-doc-segmented.md | 26 +- docs/regressions/regressions-dl19-doc-wp.md | 4 +- docs/regressions/regressions-dl19-doc.md | 38 +-- .../regressions-dl19-passage-bm25-b8.md | 4 +- .../regressions-dl19-passage-ca.md | 4 +- ...ressions-dl19-passage-cos-dpr-distil-fw.md | 6 +- ...s-dl19-passage-cos-dpr-distil-hnsw-onnx.md | 6 +- ...ssions-dl19-passage-cos-dpr-distil-hnsw.md | 6 +- ...ions-dl19-passage-cos-dpr-distil-lexlsh.md | 6 +- .../regressions-dl19-passage-docTTTTTquery.md | 26 +- .../regressions-dl19-passage-hgf-wp.md | 4 +- .../regressions-dl19-passage-openai-ada2.md | 6 +- ...passage-splade-distil-cocodenser-medium.md | 8 +- ...ressions-dl19-passage-splade-pp-ed-onnx.md | 8 +- .../regressions-dl19-passage-splade-pp-ed.md | 8 +- ...ressions-dl19-passage-splade-pp-sd-onnx.md | 8 +- .../regressions-dl19-passage-splade-pp-sd.md | 8 +- .../regressions-dl19-passage-unicoil-noexp.md | 8 +- .../regressions-dl19-passage-unicoil.md | 8 +- .../regressions-dl19-passage-wp.md | 4 +- docs/regressions/regressions-dl19-passage.md | 26 +- docs/regressions/regressions-dl20-doc-ca.md | 4 +- .../regressions-dl20-doc-docTTTTTquery.md | 14 +- .../regressions-dl20-doc-hgf-wp.md | 4 +- .../regressions-dl20-doc-segmented-ca.md | 4 +- ...ssions-dl20-doc-segmented-docTTTTTquery.md | 14 +- ...ssions-dl20-doc-segmented-unicoil-noexp.md | 8 +- .../regressions-dl20-doc-segmented-unicoil.md | 8 +- .../regressions-dl20-doc-segmented-wp.md | 4 +- .../regressions-dl20-doc-segmented.md | 26 +- docs/regressions/regressions-dl20-doc-wp.md | 4 +- docs/regressions/regressions-dl20-doc.md | 38 +-- .../regressions-dl20-passage-bm25-b8.md | 4 +- .../regressions-dl20-passage-ca.md | 4 +- ...ressions-dl20-passage-cos-dpr-distil-fw.md | 6 +- ...s-dl20-passage-cos-dpr-distil-hnsw-onnx.md | 6 +- ...ssions-dl20-passage-cos-dpr-distil-hnsw.md | 6 +- ...ions-dl20-passage-cos-dpr-distil-lexlsh.md | 6 +- .../regressions-dl20-passage-docTTTTTquery.md | 26 +- .../regressions-dl20-passage-hgf-wp.md | 4 +- .../regressions-dl20-passage-openai-ada2.md | 6 +- ...passage-splade-distil-cocodenser-medium.md | 8 +- ...ressions-dl20-passage-splade-pp-ed-onnx.md | 8 +- .../regressions-dl20-passage-splade-pp-ed.md | 8 +- ...ressions-dl20-passage-splade-pp-sd-onnx.md | 8 +- .../regressions-dl20-passage-splade-pp-sd.md | 8 +- .../regressions-dl20-passage-unicoil-noexp.md | 8 +- .../regressions-dl20-passage-unicoil.md | 8 +- .../regressions-dl20-passage-wp.md | 4 +- docs/regressions/regressions-dl20-passage.md | 26 +- .../regressions-dl21-doc-d2q-t5.md | 8 +- .../regressions-dl21-doc-segmented-d2q-t5.md | 8 +- ...ons-dl21-doc-segmented-unicoil-0shot-v2.md | 8 +- ...ssions-dl21-doc-segmented-unicoil-0shot.md | 4 +- ...21-doc-segmented-unicoil-noexp-0shot-v2.md | 8 +- ...-dl21-doc-segmented-unicoil-noexp-0shot.md | 4 +- .../regressions-dl21-doc-segmented.md | 8 +- docs/regressions/regressions-dl21-doc.md | 8 +- ...gressions-dl21-passage-augmented-d2q-t5.md | 8 +- .../regressions-dl21-passage-augmented.md | 8 +- .../regressions-dl21-passage-d2q-t5.md | 8 +- .../regressions-dl21-passage-splade-pp-ed.md | 8 +- .../regressions-dl21-passage-splade-pp-sd.md | 8 +- .../regressions-dl21-passage-unicoil-0shot.md | 8 +- ...ssions-dl21-passage-unicoil-noexp-0shot.md | 8 +- docs/regressions/regressions-dl21-passage.md | 8 +- ...gressions-dl22-passage-augmented-d2q-t5.md | 8 +- .../regressions-dl22-passage-augmented.md | 8 +- .../regressions-dl22-passage-d2q-t5.md | 8 +- .../regressions-dl22-passage-splade-pp-ed.md | 8 +- .../regressions-dl22-passage-splade-pp-sd.md | 8 +- .../regressions-dl22-passage-unicoil-0shot.md | 8 +- ...ssions-dl22-passage-unicoil-noexp-0shot.md | 8 +- docs/regressions/regressions-dl22-passage.md | 8 +- docs/regressions/regressions-fever.md | 6 +- docs/regressions/regressions-fire12-bn.md | 4 +- docs/regressions/regressions-fire12-en.md | 4 +- docs/regressions/regressions-fire12-hi.md | 4 +- docs/regressions/regressions-gov2.md | 38 +-- .../regressions-hc4-neuclir22-fa-en.md | 20 +- .../regressions-hc4-neuclir22-fa.md | 20 +- .../regressions-hc4-neuclir22-ru-en.md | 20 +- .../regressions-hc4-neuclir22-ru.md | 20 +- .../regressions-hc4-neuclir22-zh-en.md | 20 +- .../regressions-hc4-neuclir22-zh.md | 20 +- docs/regressions/regressions-hc4-v1.0-fa.md | 38 +-- docs/regressions/regressions-hc4-v1.0-ru.md | 38 +-- docs/regressions/regressions-hc4-v1.0-zh.md | 38 +-- docs/regressions/regressions-mb11.md | 26 +- docs/regressions/regressions-mb13.md | 26 +- .../regressions-miracl-v1.0-ar-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-ar.md | 4 +- .../regressions-miracl-v1.0-bn-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-bn.md | 4 +- .../regressions-miracl-v1.0-en-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-en.md | 4 +- .../regressions-miracl-v1.0-es-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-es.md | 4 +- .../regressions-miracl-v1.0-fa-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-fa.md | 4 +- .../regressions-miracl-v1.0-fi-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-fi.md | 4 +- .../regressions-miracl-v1.0-fr-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-fr.md | 4 +- .../regressions-miracl-v1.0-hi-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-hi.md | 4 +- .../regressions-miracl-v1.0-id-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-id.md | 4 +- .../regressions-miracl-v1.0-ja-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-ja.md | 4 +- .../regressions-miracl-v1.0-ko-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-ko.md | 4 +- .../regressions-miracl-v1.0-ru-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-ru.md | 4 +- .../regressions-miracl-v1.0-sw-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-sw.md | 4 +- .../regressions-miracl-v1.0-te-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-te.md | 4 +- .../regressions-miracl-v1.0-th-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-th.md | 4 +- .../regressions-miracl-v1.0-zh-aca.md | 4 +- .../regressions/regressions-miracl-v1.0-zh.md | 4 +- .../regressions-mrtydi-v1.1-ar-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-ar.md | 8 +- .../regressions-mrtydi-v1.1-bn-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-bn.md | 8 +- .../regressions-mrtydi-v1.1-en-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-en.md | 8 +- .../regressions-mrtydi-v1.1-fi-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-fi.md | 8 +- .../regressions-mrtydi-v1.1-id-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-id.md | 8 +- .../regressions-mrtydi-v1.1-ja-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-ja.md | 8 +- .../regressions-mrtydi-v1.1-ko-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-ko.md | 8 +- .../regressions-mrtydi-v1.1-ru-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-ru.md | 8 +- .../regressions-mrtydi-v1.1-sw-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-sw.md | 8 +- .../regressions-mrtydi-v1.1-te-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-te.md | 8 +- .../regressions-mrtydi-v1.1-th-aca.md | 8 +- .../regressions/regressions-mrtydi-v1.1-th.md | 8 +- .../regressions/regressions-msmarco-doc-ca.md | 4 +- .../regressions-msmarco-doc-docTTTTTquery.md | 6 +- .../regressions-msmarco-doc-hgf-wp.md | 4 +- .../regressions-msmarco-doc-segmented-ca.md | 4 +- ...ons-msmarco-doc-segmented-docTTTTTquery.md | 6 +- ...ons-msmarco-doc-segmented-unicoil-noexp.md | 4 +- ...gressions-msmarco-doc-segmented-unicoil.md | 4 +- .../regressions-msmarco-doc-segmented-wp.md | 4 +- .../regressions-msmarco-doc-segmented.md | 6 +- .../regressions/regressions-msmarco-doc-wp.md | 4 +- docs/regressions/regressions-msmarco-doc.md | 8 +- .../regressions-msmarco-passage-bm25-b8.md | 4 +- .../regressions-msmarco-passage-ca.md | 4 +- ...sions-msmarco-passage-cos-dpr-distil-fw.md | 6 +- ...smarco-passage-cos-dpr-distil-hnsw-onnx.md | 6 +- ...ons-msmarco-passage-cos-dpr-distil-hnsw.md | 6 +- ...s-msmarco-passage-cos-dpr-distil-lexlsh.md | 6 +- .../regressions-msmarco-passage-deepimpact.md | 4 +- ...ions-msmarco-passage-distill-splade-max.md | 4 +- .../regressions-msmarco-passage-doc2query.md | 6 +- ...gressions-msmarco-passage-docTTTTTquery.md | 8 +- .../regressions-msmarco-passage-hgf-wp.md | 4 +- ...regressions-msmarco-passage-openai-ada2.md | 6 +- ...passage-splade-distil-cocodenser-medium.md | 4 +- ...sions-msmarco-passage-splade-pp-ed-onnx.md | 4 +- ...egressions-msmarco-passage-splade-pp-ed.md | 4 +- ...sions-msmarco-passage-splade-pp-sd-onnx.md | 4 +- ...egressions-msmarco-passage-splade-pp-sd.md | 4 +- ...gressions-msmarco-passage-unicoil-noexp.md | 4 +- ...msmarco-passage-unicoil-tilde-expansion.md | 4 +- .../regressions-msmarco-passage-unicoil.md | 4 +- .../regressions-msmarco-passage-wp.md | 4 +- .../regressions-msmarco-passage.md | 6 +- .../regressions-msmarco-v2-doc-d2q-t5.md | 6 +- ...essions-msmarco-v2-doc-segmented-d2q-t5.md | 6 +- ...marco-v2-doc-segmented-unicoil-0shot-v2.md | 6 +- ...-msmarco-v2-doc-segmented-unicoil-0shot.md | 6 +- ...v2-doc-segmented-unicoil-noexp-0shot-v2.md | 6 +- ...co-v2-doc-segmented-unicoil-noexp-0shot.md | 6 +- .../regressions-msmarco-v2-doc-segmented.md | 6 +- .../regressions/regressions-msmarco-v2-doc.md | 6 +- ...ons-msmarco-v2-passage-augmented-d2q-t5.md | 6 +- ...egressions-msmarco-v2-passage-augmented.md | 6 +- .../regressions-msmarco-v2-passage-d2q-t5.md | 6 +- ...essions-msmarco-v2-passage-splade-pp-ed.md | 6 +- ...essions-msmarco-v2-passage-splade-pp-sd.md | 6 +- ...ssions-msmarco-v2-passage-unicoil-0shot.md | 6 +- ...-msmarco-v2-passage-unicoil-noexp-0shot.md | 6 +- .../regressions-msmarco-v2-passage.md | 6 +- .../regressions-neuclir22-fa-dt-splade.md | 20 +- .../regressions-neuclir22-fa-dt.md | 20 +- .../regressions-neuclir22-fa-qt-splade.md | 38 +-- .../regressions-neuclir22-fa-qt.md | 38 +-- .../regressions-neuclir22-ru-dt-splade.md | 20 +- .../regressions-neuclir22-ru-dt.md | 20 +- .../regressions-neuclir22-ru-qt-splade.md | 38 +-- .../regressions-neuclir22-ru-qt.md | 38 +-- .../regressions-neuclir22-zh-dt-splade.md | 20 +- .../regressions-neuclir22-zh-dt.md | 20 +- .../regressions-neuclir22-zh-qt-splade.md | 38 +-- .../regressions-neuclir22-zh-qt.md | 38 +-- docs/regressions/regressions-ntcir8-zh.md | 4 +- docs/regressions/regressions-robust05.md | 14 +- docs/regressions/regressions-trec02-ar.md | 4 +- .../regressions-wiki-all-6-3-tamber-bm25.md | 14 +- .../regressions-wikipedia-dpr-100w-bm25.md | 14 +- docs/regressions/regressions-wt10g.md | 14 +- .../analysis/AutoCompositeAnalyzer.java | 2 +- .../collection/EpidemicQACollection.java | 4 +- .../java/io/anserini/encoder/OnnxEncoder.java | 9 +- .../anserini/index/IndexHnswDenseVectors.java | 272 +++++------------- .../index/IndexInvertedDenseVectors.java | 15 +- .../io/anserini/index/IndexReaderUtils.java | 8 +- ... => HnswDenseVectorDocumentGenerator.java} | 23 +- .../InvertedDenseVectorDocumentGenerator.java | 11 +- .../io/anserini/search/SearchCollection.java | 16 +- .../search/SearchHnswDenseVectors.java | 63 ++-- .../search/SearchInvertedDenseVectors.java | 44 ++- .../InvertedDenseVectorQueryGenerator.java | 3 +- src/main/python/run_regression.py | 6 +- .../dl19-passage-cos-dpr-distil-fw.yaml | 2 +- ...dl19-passage-cos-dpr-distil-hnsw-onnx.yaml | 4 +- .../dl19-passage-cos-dpr-distil-hnsw.yaml | 4 +- .../dl19-passage-cos-dpr-distil-lexlsh.yaml | 2 +- .../regression/dl19-passage-openai-ada2.yaml | 4 +- .../dl20-passage-cos-dpr-distil-fw.yaml | 2 +- ...dl20-passage-cos-dpr-distil-hnsw-onnx.yaml | 4 +- .../dl20-passage-cos-dpr-distil-hnsw.yaml | 4 +- .../dl20-passage-cos-dpr-distil-lexlsh.yaml | 2 +- .../regression/dl20-passage-openai-ada2.yaml | 4 +- .../msmarco-passage-cos-dpr-distil-fw.yaml | 2 +- ...arco-passage-cos-dpr-distil-hnsw-onnx.yaml | 4 +- .../msmarco-passage-cos-dpr-distil-hnsw.yaml | 4 +- ...msmarco-passage-cos-dpr-distil-lexlsh.yaml | 2 +- .../msmarco-passage-openai-ada2.yaml | 4 +- .../analysis/AutoCompositeAnalyzerTest.java | 9 +- .../analysis/CompositeAnalyzerTest.java | 2 - .../collection/EpidemicQACollectionTest.java | 1 + src/test/java/io/anserini/doc/DataModel.java | 4 +- .../index/BasicIndexOperationsTest.java | 16 ++ .../io/anserini/index/CloneIndexTest.java | 16 ++ .../index/IndexHnswDenseVectorsTest.java | 63 ++-- .../index/IndexInvertedDenseVectorsTest.java | 30 +- .../io/anserini/index/SimpleIndexerTest.java | 7 + .../io/anserini/integration/EndToEndTest.java | 2 +- .../integration/TweetEndToEndTest.java | 8 + .../anserini/search/SearchCollectionTest.java | 24 +- .../search/SearchHnswDenseVectorsTest.java | 97 +++++++ .../SearchInvertedDenseVectorsTest.java | 64 +++-- .../query/PhraseQueryGeneratorTest.java | 1 - ...pics.msmarco-passage-dev-openai-ada2.jsonl | 2 + 426 files changed, 1895 insertions(+), 1913 deletions(-) rename src/main/java/io/anserini/index/generator/{LuceneDenseVectorDocumentGenerator.java => HnswDenseVectorDocumentGenerator.java} (80%) create mode 100644 src/test/java/io/anserini/search/SearchHnswDenseVectorsTest.java create mode 100644 src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-openai-ada2.jsonl diff --git a/docs/regressions/regressions-backgroundlinking18.md b/docs/regressions/regressions-backgroundlinking18.md index ad53b02368..115ca58b57 100644 --- a/docs/regressions/regressions-backgroundlinking18.md +++ b/docs/regressions/regressions-backgroundlinking18.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection WashingtonPostCollection \ -input /path/to/wapo.v2 \ - -index indexes/lucene-index.wapo.v2/ \ -generator WashingtonPostGenerator \ + -index indexes/lucene-index.wapo.v2/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.wapo.v2 & ``` @@ -45,21 +45,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.backgroundlinking18.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v2.bm25.topics.backgroundlinking18.txt \ -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.backgroundlinking18.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v2.bm25+rm3.topics.backgroundlinking18.txt \ -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.backgroundlinking18.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v2.bm25+rm3+df.topics.backgroundlinking18.txt \ -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 & ``` diff --git a/docs/regressions/regressions-backgroundlinking19.md b/docs/regressions/regressions-backgroundlinking19.md index 201a8d195d..60f7c07774 100644 --- a/docs/regressions/regressions-backgroundlinking19.md +++ b/docs/regressions/regressions-backgroundlinking19.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection WashingtonPostCollection \ -input /path/to/wapo.v2 \ - -index indexes/lucene-index.wapo.v2/ \ -generator WashingtonPostGenerator \ + -index indexes/lucene-index.wapo.v2/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.wapo.v2 & ``` @@ -45,21 +45,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.backgroundlinking19.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v2.bm25.topics.backgroundlinking19.txt \ -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.backgroundlinking19.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v2.bm25+rm3.topics.backgroundlinking19.txt \ -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.backgroundlinking19.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v2.bm25+rm3+df.topics.backgroundlinking19.txt \ -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 & ``` diff --git a/docs/regressions/regressions-backgroundlinking20.md b/docs/regressions/regressions-backgroundlinking20.md index 3e82631ea9..ba62761a94 100644 --- a/docs/regressions/regressions-backgroundlinking20.md +++ b/docs/regressions/regressions-backgroundlinking20.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection WashingtonPostCollection \ -input /path/to/wapo.v3 \ - -index indexes/lucene-index.wapo.v3/ \ -generator WashingtonPostGenerator \ + -index indexes/lucene-index.wapo.v3/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.wapo.v3 & ``` @@ -45,21 +45,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v3/ \ -topics tools/topics-and-qrels/topics.backgroundlinking20.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v3.bm25.topics.backgroundlinking20.txt \ -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v3/ \ -topics tools/topics-and-qrels/topics.backgroundlinking20.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v3.bm25+rm3.topics.backgroundlinking20.txt \ -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v3/ \ -topics tools/topics-and-qrels/topics.backgroundlinking20.txt \ - -topicreader BackgroundLinking \ + -topicReader BackgroundLinking \ -output runs/run.wapo.v3.bm25+rm3+df.topics.backgroundlinking20.txt \ -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-arguana-flat-wp.md index 63197dec7a..0eca61c98f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-arguana-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-arguana-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-arguana-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-arguana-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-arguana-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-arguana-flat-wp.bm25.topics.beir-v1.0.0-arguana.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana-flat.md b/docs/regressions/regressions-beir-v1.0.0-arguana-flat.md index a7cbcd9dbe..0c8dcc2c9b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-arguana-flat \ - -index indexes/lucene-index.beir-v1.0.0-arguana-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-arguana-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-arguana-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-arguana-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-arguana-flat.bm25.topics.beir-v1.0.0-arguana.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana-multifield.md b/docs/regressions/regressions-beir-v1.0.0-arguana-multifield.md index affdb1beee..39fa6814e9 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-arguana-multifield \ - -index indexes/lucene-index.beir-v1.0.0-arguana-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-arguana-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-arguana-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-arguana-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-arguana-multifield.bm25.topics.beir-v1.0.0-arguana.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-arguana-splade-distil-cocodenser-medium.md index 904db5d7a9..44615236e5 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana-splade-distil-cocodenser-medium.md @@ -48,8 +48,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-arguana-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-arguana-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-arguana-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-arguana-splade_distil_cocodenser_medium & ``` @@ -71,7 +71,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-arguana-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-arguana-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-arguana.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-arguana-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-arguana-unicoil-noexp.md index f975ab0c14..42921530a8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-arguana-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-arguana-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-arguana-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-arguana-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-arguana-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-arguana-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-arguana-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-arguana.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-arguana-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-arguana.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-bioasq-flat-wp.md index addcc88402..4b836eb996 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-bioasq-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-bioasq-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-bioasq-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-bioasq-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-bioasq-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-bioasq-flat-wp.bm25.topics.beir-v1.0.0-bioasq.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq-flat.md b/docs/regressions/regressions-beir-v1.0.0-bioasq-flat.md index 31d7f89081..504bcbc16d 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-bioasq-flat \ - -index indexes/lucene-index.beir-v1.0.0-bioasq-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-bioasq-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-bioasq-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-bioasq-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-bioasq-flat.bm25.topics.beir-v1.0.0-bioasq.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq-multifield.md b/docs/regressions/regressions-beir-v1.0.0-bioasq-multifield.md index 4795cfe049..e6131fcb6c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-bioasq-multifield \ - -index indexes/lucene-index.beir-v1.0.0-bioasq-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-bioasq-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-bioasq-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-bioasq-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-bioasq-multifield.bm25.topics.beir-v1.0.0-bioasq.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-bioasq-splade-distil-cocodenser-medium.md index b84fd9d4a8..bc5e96d820 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-bioasq-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-bioasq-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-bioasq-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-bioasq-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-bioasq-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-bioasq-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-bioasq.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-bioasq-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-bioasq-unicoil-noexp.md index 72fdd6409c..029f25e9a7 100644 --- a/docs/regressions/regressions-beir-v1.0.0-bioasq-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-bioasq-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-bioasq-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-bioasq-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-bioasq-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-bioasq-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-bioasq-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-bioasq.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-bioasq-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-bioasq.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever-flat-wp.md index a745ff00a8..88d31cbb4c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-climate-fever-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-climate-fever-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-climate-fever-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-climate-fever-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-climate-fever-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-climate-fever-flat-wp.bm25.topics.beir-v1.0.0-climate-fever.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever-flat.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever-flat.md index 11768beeee..fddcf59581 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-climate-fever-flat \ - -index indexes/lucene-index.beir-v1.0.0-climate-fever-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-climate-fever-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-climate-fever-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-climate-fever-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-climate-fever-flat.bm25.topics.beir-v1.0.0-climate-fever.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever-multifield.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever-multifield.md index b21a32c271..83dcfb039c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-climate-fever-multifield \ - -index indexes/lucene-index.beir-v1.0.0-climate-fever-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-climate-fever-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-climate-fever-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-climate-fever-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-climate-fever-multifield.bm25.topics.beir-v1.0.0-climate-fever.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever-splade-distil-cocodenser-medium.md index 924d599870..6f17e7b527 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-climate-fever-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-climate-fever-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-climate-fever-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-climate-fever-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-climate-fever-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-climate-fever-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-climate-fever.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-climate-fever-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-climate-fever-unicoil-noexp.md index 9310c4e6e8..c6f7bba4a0 100644 --- a/docs/regressions/regressions-beir-v1.0.0-climate-fever-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-climate-fever-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-climate-fever-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-climate-fever-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-climate-fever-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-climate-fever-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-climate-fever-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-climate-fever.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-climate-fever-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-climate-fever.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-flat-wp.md index 0310ae957c..dc4da4d5cc 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-android-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-android-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-android.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-flat.md index d3e609b43e..960bf62f6f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-android-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-android-flat.bm25.topics.beir-v1.0.0-cqadupstack-android.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-multifield.md index d4eccafeec..d0048a5ca6 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-android-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-android-multifield.bm25.topics.beir-v1.0.0-cqadupstack-android.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-splade-distil-cocodenser-medium.md index 5af560d337..bc2f4b3b7c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-android-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-android-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-android.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-unicoil-noexp.md index 308e13a8aa..f57784e92c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-android-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-android-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-android-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-android-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-android.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-android-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-android.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-flat-wp.md index 808c0f635c..bd42d98e62 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-english-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-english-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-english.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-flat.md index f4dd574c90..33ee26280e 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-english-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-english-flat.bm25.topics.beir-v1.0.0-cqadupstack-english.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-multifield.md index 350e191340..f67e1a3fd4 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-english-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-english-multifield.bm25.topics.beir-v1.0.0-cqadupstack-english.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-splade-distil-cocodenser-medium.md index a738000172..7e6d26ce7b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-english-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-english-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-english.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-unicoil-noexp.md index 227b7febdd..7d423b290b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-english-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-english-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-english-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-english-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-english.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-english-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-english.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-flat-wp.md index 44b08b39f0..ce6e1f1715 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-gaming-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gaming-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-gaming.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-flat.md index c9e3cd50e7..ec9f0212c8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-gaming-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gaming-flat.bm25.topics.beir-v1.0.0-cqadupstack-gaming.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-multifield.md index 8c4a2008ea..086fbfc951 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-gaming-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gaming-multifield.bm25.topics.beir-v1.0.0-cqadupstack-gaming.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-splade-distil-cocodenser-medium.md index 4b3f6c2334..b6df921ced 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-gaming-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gaming-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-gaming.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-unicoil-noexp.md index 8d67a5bb36..f37d38d8c9 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gaming-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gaming-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-gaming-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gaming-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gaming.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gaming-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-gaming.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-flat-wp.md index 6247693b35..9d2c2c0361 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-gis-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gis-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-gis.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-flat.md index 6cd7105b3d..b4016d12bc 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-gis-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gis-flat.bm25.topics.beir-v1.0.0-cqadupstack-gis.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-multifield.md index cc5d35c8a2..9dd16935c8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-gis-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gis-multifield.bm25.topics.beir-v1.0.0-cqadupstack-gis.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-splade-distil-cocodenser-medium.md index 24b1c5b978..207d446fef 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-gis-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gis-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-gis.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-unicoil-noexp.md index 32b7a82db2..ab0b6cbba9 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-gis-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-gis-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-gis-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-gis-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-gis.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-gis-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-gis.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-flat-wp.md index d4fbc0ebd1..e3e4c2b795 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-mathematica-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-mathematica-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-mathematica.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-flat.md index 060f1bfce3..f8e1acbb72 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-mathematica-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-mathematica-flat.bm25.topics.beir-v1.0.0-cqadupstack-mathematica.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-multifield.md index f87268e287..277166aca0 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-mathematica-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-mathematica-multifield.bm25.topics.beir-v1.0.0-cqadupstack-mathematica.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-splade-distil-cocodenser-medium.md index 06fb8a636f..20a199ce24 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-mathematica-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-mathematica-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-mathematica.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp.md index e7f094b22c..8e38d4c913 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-mathematica.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-mathematica-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-mathematica.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-flat-wp.md index 0f24413e21..99f8574eb9 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-physics-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-physics-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-physics.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-flat.md index 84ac6dc82b..454dd5ee73 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-physics-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-physics-flat.bm25.topics.beir-v1.0.0-cqadupstack-physics.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-multifield.md index 4980e923d7..6a2e4a9588 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-physics-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-physics-multifield.bm25.topics.beir-v1.0.0-cqadupstack-physics.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-splade-distil-cocodenser-medium.md index bfa11b40ae..a35d017301 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-physics-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-physics-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-physics.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-unicoil-noexp.md index d69cb88bc5..ffed8923c5 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-physics-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-physics-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-physics-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-physics-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-physics.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-physics-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-physics.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-flat-wp.md index 44d2012d3d..c2b3e1c113 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-programmers-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-programmers-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-programmers.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-flat.md index 9bca89a3c9..e4d184526c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-programmers-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-programmers-flat.bm25.topics.beir-v1.0.0-cqadupstack-programmers.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-multifield.md index b5bad4d553..d28ad75220 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-programmers-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-programmers-multifield.bm25.topics.beir-v1.0.0-cqadupstack-programmers.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-splade-distil-cocodenser-medium.md index 13c1044d8b..be89a18291 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-programmers-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-programmers-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-programmers.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-unicoil-noexp.md index d9cbb6b026..4f575c88c3 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-programmers-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-programmers-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-programmers-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-programmers-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-programmers.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-programmers-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-programmers.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-flat-wp.md index 1df9ef5fe5..8c6e945254 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-stats-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-stats-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-stats.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-flat.md index 4ba693e58d..042c351faa 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-stats-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-stats-flat.bm25.topics.beir-v1.0.0-cqadupstack-stats.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-multifield.md index ff8ff5bf20..f915d8c4d5 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-stats-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-stats-multifield.bm25.topics.beir-v1.0.0-cqadupstack-stats.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-splade-distil-cocodenser-medium.md index 625e4fcd76..a49d9f25c1 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-stats-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-stats-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-stats.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-unicoil-noexp.md index 00f5166834..bff4728f29 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-stats-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-stats-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-stats-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-stats-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-stats.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-stats-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-stats.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-flat-wp.md index 453a597192..36bf47b271 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-tex-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-tex-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-tex.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-flat.md index e29127165a..76a3bac5d5 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-tex-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-tex-flat.bm25.topics.beir-v1.0.0-cqadupstack-tex.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-multifield.md index 695b885c6f..7038287779 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-tex-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-tex-multifield.bm25.topics.beir-v1.0.0-cqadupstack-tex.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-splade-distil-cocodenser-medium.md index 2b83e5a96f..92f0947662 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-tex-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-tex-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-tex.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-unicoil-noexp.md index a246040edb..784e508393 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-tex-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-tex-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-tex-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-tex-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-tex.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-tex-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-tex.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-flat-wp.md index fcb07e3dbe..b1032517d8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-unix-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-unix-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-unix.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-flat.md index 463d703b1c..487ae086f0 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-unix-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-unix-flat.bm25.topics.beir-v1.0.0-cqadupstack-unix.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-multifield.md index a4d9561846..781fdf2a3e 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-unix-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-unix-multifield.bm25.topics.beir-v1.0.0-cqadupstack-unix.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-splade-distil-cocodenser-medium.md index 90246503d4..aa8b0cc849 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-unix-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-unix-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-unix.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-unicoil-noexp.md index 4f3ec0d53b..36cf39c690 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-unix-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-unix-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-unix-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-unix-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-unix.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-unix-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-unix.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-flat-wp.md index 7087309d1b..95e93bb981 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-webmasters-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-webmasters-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-webmasters.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-flat.md index 513bd74513..e23b0ad100 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-webmasters-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-webmasters-flat.bm25.topics.beir-v1.0.0-cqadupstack-webmasters.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-multifield.md index 6cb4726616..450c76eb6b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-webmasters-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-webmasters-multifield.bm25.topics.beir-v1.0.0-cqadupstack-webmasters.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-splade-distil-cocodenser-medium.md index 9af12dc94e..4a4efe1d9c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-webmasters-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-webmasters-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-webmasters.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp.md index 3006d93230..911eb6f1ed 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-webmasters.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-webmasters-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-webmasters.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-flat-wp.md index d320ac8f98..034b182d17 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-wordpress-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-wordpress-flat-wp.bm25.topics.beir-v1.0.0-cqadupstack-wordpress.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-flat.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-flat.md index de03f016f8..6c352ec753 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress-flat \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-cqadupstack-wordpress-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-wordpress-flat.bm25.topics.beir-v1.0.0-cqadupstack-wordpress.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-multifield.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-multifield.md index 08a2576291..8182f83179 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress-multifield \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-cqadupstack-wordpress-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-wordpress-multifield.bm25.topics.beir-v1.0.0-cqadupstack-wordpress.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-splade-distil-cocodenser-medium.md index 81bcd00454..fa8eb479b7 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-wordpress-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-wordpress-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-cqadupstack-wordpress.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp.md index d0d40eb47d..c8267c535f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-cqadupstack-wordpress.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-cqadupstack-wordpress-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-cqadupstack-wordpress.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-flat-wp.md index ba94e811e1..d6c55c7429 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-dbpedia-entity-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-dbpedia-entity-flat-wp.bm25.topics.beir-v1.0.0-dbpedia-entity.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-flat.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-flat.md index 0d74397008..a5de05c687 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity-flat \ - -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-dbpedia-entity-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-dbpedia-entity-flat.bm25.topics.beir-v1.0.0-dbpedia-entity.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-multifield.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-multifield.md index d86b32c33d..12632d4fc7 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity-multifield \ - -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-dbpedia-entity-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-dbpedia-entity-multifield.bm25.topics.beir-v1.0.0-dbpedia-entity.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-splade-distil-cocodenser-medium.md index f98e63a607..7ca380fe55 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-dbpedia-entity-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-dbpedia-entity-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-dbpedia-entity.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-unicoil-noexp.md index ae0cd97a61..f85d7a9c62 100644 --- a/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-dbpedia-entity-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-dbpedia-entity-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-dbpedia-entity-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-dbpedia-entity-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-dbpedia-entity.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-dbpedia-entity-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-dbpedia-entity.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fever-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-fever-flat-wp.md index 24f9e77abb..70450790e6 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-fever-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-fever-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fever-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-fever-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fever-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fever-flat-wp.bm25.topics.beir-v1.0.0-fever.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fever-flat.md b/docs/regressions/regressions-beir-v1.0.0-fever-flat.md index 9675f76966..e46abb1ae7 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-fever-flat \ - -index indexes/lucene-index.beir-v1.0.0-fever-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fever-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-fever-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fever-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fever-flat.bm25.topics.beir-v1.0.0-fever.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fever-multifield.md b/docs/regressions/regressions-beir-v1.0.0-fever-multifield.md index 068932f2af..635a049952 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-fever-multifield \ - -index indexes/lucene-index.beir-v1.0.0-fever-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fever-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-fever-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fever-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fever-multifield.bm25.topics.beir-v1.0.0-fever.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fever-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-fever-splade-distil-cocodenser-medium.md index a4eea5bf72..e96ed4675f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-fever-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-fever-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fever-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-fever-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fever-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fever-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-fever.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fever-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-fever-unicoil-noexp.md index 902a1f3b19..1a0cc18ed8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fever-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-fever-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-fever-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-fever-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fever-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-fever-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fever-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fever.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fever-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-fever.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-fiqa-flat-wp.md index 1c49d7792e..02504ed9af 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-fiqa-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-fiqa-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fiqa-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-fiqa-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fiqa-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fiqa-flat-wp.bm25.topics.beir-v1.0.0-fiqa.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa-flat.md b/docs/regressions/regressions-beir-v1.0.0-fiqa-flat.md index 078d996b3a..c2c1ab7af5 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-fiqa-flat \ - -index indexes/lucene-index.beir-v1.0.0-fiqa-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fiqa-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-fiqa-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fiqa-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fiqa-flat.bm25.topics.beir-v1.0.0-fiqa.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa-multifield.md b/docs/regressions/regressions-beir-v1.0.0-fiqa-multifield.md index c2c66ff133..f300f80daa 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-fiqa-multifield \ - -index indexes/lucene-index.beir-v1.0.0-fiqa-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fiqa-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-fiqa-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fiqa-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fiqa-multifield.bm25.topics.beir-v1.0.0-fiqa.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-fiqa-splade-distil-cocodenser-medium.md index 5b6d854a29..49913128a8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-fiqa-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-fiqa-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fiqa-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-fiqa-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fiqa-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fiqa-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-fiqa.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-fiqa-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-fiqa-unicoil-noexp.md index e3d8857e29..9c2b85ec95 100644 --- a/docs/regressions/regressions-beir-v1.0.0-fiqa-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-fiqa-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-fiqa-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-fiqa-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-fiqa-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-fiqa-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-fiqa-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-fiqa.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-fiqa-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-fiqa.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-flat-wp.md index 44191cb4ee..765f99941c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-hotpotqa-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-hotpotqa-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-hotpotqa-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-hotpotqa-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-hotpotqa-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-hotpotqa-flat-wp.bm25.topics.beir-v1.0.0-hotpotqa.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-flat.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-flat.md index ceefbccdfb..4651adb45b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-hotpotqa-flat \ - -index indexes/lucene-index.beir-v1.0.0-hotpotqa-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-hotpotqa-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-hotpotqa-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-hotpotqa-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-hotpotqa-flat.bm25.topics.beir-v1.0.0-hotpotqa.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-multifield.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-multifield.md index e7078a941e..75f4f80130 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-hotpotqa-multifield \ - -index indexes/lucene-index.beir-v1.0.0-hotpotqa-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-hotpotqa-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-hotpotqa-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-hotpotqa-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-hotpotqa-multifield.bm25.topics.beir-v1.0.0-hotpotqa.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-splade-distil-cocodenser-medium.md index f92548d647..6e8bdebf6a 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-hotpotqa-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-hotpotqa-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-hotpotqa-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-hotpotqa-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-hotpotqa-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-hotpotqa-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-hotpotqa.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-unicoil-noexp.md index b2df25a461..775d45e071 100644 --- a/docs/regressions/regressions-beir-v1.0.0-hotpotqa-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-hotpotqa-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-hotpotqa-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-hotpotqa-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-hotpotqa-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-hotpotqa-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-hotpotqa-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-hotpotqa.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-hotpotqa-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-hotpotqa.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-flat-wp.md index 97d0edd863..669f602faa 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-nfcorpus-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-nfcorpus-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nfcorpus-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-nfcorpus-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nfcorpus-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nfcorpus-flat-wp.bm25.topics.beir-v1.0.0-nfcorpus.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-flat.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-flat.md index a64587f879..b0d28ee403 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-nfcorpus-flat \ - -index indexes/lucene-index.beir-v1.0.0-nfcorpus-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nfcorpus-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-nfcorpus-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nfcorpus-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nfcorpus-flat.bm25.topics.beir-v1.0.0-nfcorpus.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-multifield.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-multifield.md index 385d5411d0..c0d2e8aaf8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-nfcorpus-multifield \ - -index indexes/lucene-index.beir-v1.0.0-nfcorpus-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nfcorpus-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-nfcorpus-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nfcorpus-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nfcorpus-multifield.bm25.topics.beir-v1.0.0-nfcorpus.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-splade-distil-cocodenser-medium.md index 40854a4835..64808c1546 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-nfcorpus-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-nfcorpus-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nfcorpus-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-nfcorpus-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nfcorpus-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nfcorpus-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-nfcorpus.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-unicoil-noexp.md index 856bfa2460..55663829fd 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nfcorpus-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-nfcorpus-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-nfcorpus-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-nfcorpus-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nfcorpus-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-nfcorpus-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nfcorpus-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nfcorpus.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nfcorpus-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-nfcorpus.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nq-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-nq-flat-wp.md index 6c6dbf243b..7a5d148667 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-nq-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-nq-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nq-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-nq-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nq-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nq-flat-wp.bm25.topics.beir-v1.0.0-nq.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nq-flat.md b/docs/regressions/regressions-beir-v1.0.0-nq-flat.md index 7aa8738fe2..179044ef89 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-nq-flat \ - -index indexes/lucene-index.beir-v1.0.0-nq-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nq-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-nq-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nq-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nq-flat.bm25.topics.beir-v1.0.0-nq.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nq-multifield.md b/docs/regressions/regressions-beir-v1.0.0-nq-multifield.md index 4990f88f89..5472e3adbe 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-nq-multifield \ - -index indexes/lucene-index.beir-v1.0.0-nq-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nq-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-nq-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nq-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nq-multifield.bm25.topics.beir-v1.0.0-nq.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nq-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-nq-splade-distil-cocodenser-medium.md index 955b93e8a0..7e56289daf 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-nq-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-nq-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nq-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-nq-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nq-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nq-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-nq.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-nq-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-nq-unicoil-noexp.md index df0b0f39ea..d6eddd4236 100644 --- a/docs/regressions/regressions-beir-v1.0.0-nq-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-nq-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-nq-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-nq-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-nq-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-nq-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-nq-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-nq.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-nq-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-nq.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-quora-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-quora-flat-wp.md index 1fc0449b3c..e79bc7040d 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-quora-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-quora-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-quora-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-quora-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-quora-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-quora-flat-wp.bm25.topics.beir-v1.0.0-quora.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-quora-flat.md b/docs/regressions/regressions-beir-v1.0.0-quora-flat.md index eb0d27e43d..ec1b917818 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-quora-flat \ - -index indexes/lucene-index.beir-v1.0.0-quora-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-quora-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-quora-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-quora-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-quora-flat.bm25.topics.beir-v1.0.0-quora.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-quora-multifield.md b/docs/regressions/regressions-beir-v1.0.0-quora-multifield.md index 6ca7c7c7ee..7fb3caf72a 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-quora-multifield \ - -index indexes/lucene-index.beir-v1.0.0-quora-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-quora-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-quora-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-quora-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-quora-multifield.bm25.topics.beir-v1.0.0-quora.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-quora-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-quora-splade-distil-cocodenser-medium.md index 9e0d6af5a0..bddc8a6a10 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-quora-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-quora-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-quora-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-quora-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-quora-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-quora-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-quora.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-quora-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-quora-unicoil-noexp.md index fa6fcb040c..fea520934b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-quora-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-quora-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-quora-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-quora-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-quora-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-quora-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-quora-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-quora.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-quora-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-quora.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-robust04-flat-wp.md index 4ea23d7350..9c9dbc364c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-robust04-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-robust04-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-robust04-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-robust04-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-robust04-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-robust04-flat-wp.bm25.topics.beir-v1.0.0-robust04.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04-flat.md b/docs/regressions/regressions-beir-v1.0.0-robust04-flat.md index 12e46a5de0..eb3c262d60 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-robust04-flat \ - -index indexes/lucene-index.beir-v1.0.0-robust04-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-robust04-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-robust04-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-robust04-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-robust04-flat.bm25.topics.beir-v1.0.0-robust04.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04-multifield.md b/docs/regressions/regressions-beir-v1.0.0-robust04-multifield.md index 5663ba0a2d..be4440e950 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-robust04-multifield \ - -index indexes/lucene-index.beir-v1.0.0-robust04-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-robust04-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-robust04-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-robust04-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-robust04-multifield.bm25.topics.beir-v1.0.0-robust04.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-robust04-splade-distil-cocodenser-medium.md index 2b2afea835..8bc670a5be 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-robust04-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-robust04-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-robust04-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-robust04-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-robust04-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-robust04-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-robust04.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-robust04-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-robust04-unicoil-noexp.md index cec9e5c22c..68ba473fe2 100644 --- a/docs/regressions/regressions-beir-v1.0.0-robust04-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-robust04-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-robust04-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-robust04-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-robust04-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-robust04-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-robust04-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-robust04.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-robust04-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-robust04.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-scidocs-flat-wp.md index c6100084a5..245297f6a4 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-scidocs-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-scidocs-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scidocs-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-scidocs-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scidocs-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scidocs-flat-wp.bm25.topics.beir-v1.0.0-scidocs.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs-flat.md b/docs/regressions/regressions-beir-v1.0.0-scidocs-flat.md index 2e89a9eecc..422284fcb8 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-scidocs-flat \ - -index indexes/lucene-index.beir-v1.0.0-scidocs-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scidocs-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-scidocs-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scidocs-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scidocs-flat.bm25.topics.beir-v1.0.0-scidocs.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs-multifield.md b/docs/regressions/regressions-beir-v1.0.0-scidocs-multifield.md index 3b8c3fa443..30771e6d35 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-scidocs-multifield \ - -index indexes/lucene-index.beir-v1.0.0-scidocs-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scidocs-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-scidocs-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scidocs-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scidocs-multifield.bm25.topics.beir-v1.0.0-scidocs.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-scidocs-splade-distil-cocodenser-medium.md index 2184e00c34..2526e7080d 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-scidocs-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-scidocs-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scidocs-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-scidocs-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scidocs-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scidocs-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-scidocs.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scidocs-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-scidocs-unicoil-noexp.md index e60c7b8b64..749893f8af 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scidocs-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-scidocs-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-scidocs-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-scidocs-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scidocs-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-scidocs-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scidocs-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scidocs.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scidocs-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-scidocs.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-scifact-flat-wp.md index ee9e6b6ca0..1906931ad3 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-scifact-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-scifact-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scifact-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-scifact-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scifact-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scifact-flat-wp.bm25.topics.beir-v1.0.0-scifact.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact-flat.md b/docs/regressions/regressions-beir-v1.0.0-scifact-flat.md index 954544305e..7c6fb8023f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-scifact-flat \ - -index indexes/lucene-index.beir-v1.0.0-scifact-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scifact-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-scifact-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scifact-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scifact-flat.bm25.topics.beir-v1.0.0-scifact.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact-multifield.md b/docs/regressions/regressions-beir-v1.0.0-scifact-multifield.md index bf07a8bb2d..20558c9cb3 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-scifact-multifield \ - -index indexes/lucene-index.beir-v1.0.0-scifact-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scifact-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-scifact-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scifact-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scifact-multifield.bm25.topics.beir-v1.0.0-scifact.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-scifact-splade-distil-cocodenser-medium.md index a3884cc477..7e290999c0 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-scifact-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-scifact-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scifact-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-scifact-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scifact-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scifact-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-scifact.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-scifact-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-scifact-unicoil-noexp.md index 6069a44903..406a21b380 100644 --- a/docs/regressions/regressions-beir-v1.0.0-scifact-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-scifact-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-scifact-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-scifact-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-scifact-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-scifact-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-scifact-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-scifact.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-scifact-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-scifact.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-signal1m-flat-wp.md index b53e765103..7792908172 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-signal1m-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-signal1m-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-signal1m-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-signal1m-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-signal1m-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-signal1m-flat-wp.bm25.topics.beir-v1.0.0-signal1m.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m-flat.md b/docs/regressions/regressions-beir-v1.0.0-signal1m-flat.md index bd77f9891a..beb5fe1c42 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-signal1m-flat \ - -index indexes/lucene-index.beir-v1.0.0-signal1m-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-signal1m-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-signal1m-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-signal1m-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-signal1m-flat.bm25.topics.beir-v1.0.0-signal1m.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m-multifield.md b/docs/regressions/regressions-beir-v1.0.0-signal1m-multifield.md index 598efc3d56..c2e8718f5b 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-signal1m-multifield \ - -index indexes/lucene-index.beir-v1.0.0-signal1m-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-signal1m-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-signal1m-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-signal1m-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-signal1m-multifield.bm25.topics.beir-v1.0.0-signal1m.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-signal1m-splade-distil-cocodenser-medium.md index ff339e7968..90a6e5f20f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-signal1m-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-signal1m-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-signal1m-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-signal1m-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-signal1m-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-signal1m-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-signal1m.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-signal1m-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-signal1m-unicoil-noexp.md index cd1ea691a6..8b9a382683 100644 --- a/docs/regressions/regressions-beir-v1.0.0-signal1m-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-signal1m-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-signal1m-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-signal1m-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-signal1m-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-signal1m-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-signal1m-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-signal1m.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-signal1m-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-signal1m.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid-flat-wp.md index 667f32b6b9..c0d9fef8b1 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-trec-covid-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-trec-covid-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-covid-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-trec-covid-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-covid-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-covid-flat-wp.bm25.topics.beir-v1.0.0-trec-covid.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid-flat.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid-flat.md index bef636d839..9428a5fffa 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-trec-covid-flat \ - -index indexes/lucene-index.beir-v1.0.0-trec-covid-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-covid-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-trec-covid-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-covid-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-covid-flat.bm25.topics.beir-v1.0.0-trec-covid.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid-multifield.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid-multifield.md index 7d928f0b31..3a680d3e4c 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-trec-covid-multifield \ - -index indexes/lucene-index.beir-v1.0.0-trec-covid-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-covid-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-trec-covid-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-covid-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-covid-multifield.bm25.topics.beir-v1.0.0-trec-covid.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid-splade-distil-cocodenser-medium.md index 2876d35926..f7b2e517ca 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-trec-covid-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-trec-covid-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-covid-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-trec-covid-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-covid-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-covid-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-trec-covid.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-covid-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-trec-covid-unicoil-noexp.md index 747029c197..d1ff26ba91 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-covid-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-covid-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-trec-covid-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-trec-covid-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-covid-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-trec-covid-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-covid-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-covid.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-covid-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-trec-covid.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-trec-news-flat-wp.md index cc71ac3a0c..49e09c4041 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-trec-news-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-trec-news-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-news-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-trec-news-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-news-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-news-flat-wp.bm25.topics.beir-v1.0.0-trec-news.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news-flat.md b/docs/regressions/regressions-beir-v1.0.0-trec-news-flat.md index 7a6ef70a55..cfa7e40fe5 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-trec-news-flat \ - -index indexes/lucene-index.beir-v1.0.0-trec-news-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-news-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-trec-news-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-news-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-news-flat.bm25.topics.beir-v1.0.0-trec-news.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news-multifield.md b/docs/regressions/regressions-beir-v1.0.0-trec-news-multifield.md index fed56f82fe..79227fbfdb 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-trec-news-multifield \ - -index indexes/lucene-index.beir-v1.0.0-trec-news-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-news-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-trec-news-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-news-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-news-multifield.bm25.topics.beir-v1.0.0-trec-news.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-trec-news-splade-distil-cocodenser-medium.md index e1f4346445..b3ccf62f20 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-trec-news-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-trec-news-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-news-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-trec-news-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-news-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-news-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-trec-news.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-trec-news-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-trec-news-unicoil-noexp.md index de0a61cb0d..9dc94f3923 100644 --- a/docs/regressions/regressions-beir-v1.0.0-trec-news-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-trec-news-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-trec-news-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-trec-news-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-trec-news-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-trec-news-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-trec-news-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-trec-news.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-trec-news-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-trec-news.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-flat-wp.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-flat-wp.md index 735b4b2721..44eb409a40 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-flat-wp.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-flat-wp.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-webis-touche2020-flat-wp \ - -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-flat-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-flat-wp/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.beir-v1.0.0-webis-touche2020-flat-wp & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-flat-wp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.wp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-webis-touche2020-flat-wp.bm25.topics.beir-v1.0.0-webis-touche2020.test.wp.txt \ -bm25 -removeQuery -pretokenized & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-flat.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-flat.md index 6d79cd0d6f..6377b84355 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-flat.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-flat.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirFlatCollection \ -input /path/to/beir-v1.0.0-webis-touche2020-flat \ - -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-flat/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-flat/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.beir-v1.0.0-webis-touche2020-flat & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-flat/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-webis-touche2020-flat.bm25.topics.beir-v1.0.0-webis-touche2020.test.txt \ -bm25 -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-multifield.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-multifield.md index 8473a7af01..ce0510d573 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-multifield.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-multifield.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection BeirMultifieldCollection \ -input /path/to/beir-v1.0.0-webis-touche2020-multifield \ - -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-multifield/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-multifield/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -fields title \ >& logs/log.beir-v1.0.0-webis-touche2020-multifield & ``` @@ -39,7 +39,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-multifield/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-webis-touche2020-multifield.bm25.topics.beir-v1.0.0-webis-touche2020.test.txt \ -bm25 -removeQuery -hits 1000 -fields contents=1.0 title=1.0 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-splade-distil-cocodenser-medium.md index 97cd2f3ee3..4f3d7db412 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-splade-distil-cocodenser-medium.md @@ -49,8 +49,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-webis-touche2020-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-webis-touche2020-splade_distil_cocodenser_medium & ``` @@ -72,7 +72,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-webis-touche2020-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.beir-v1.0.0-webis-touche2020.test.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-unicoil-noexp.md b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-unicoil-noexp.md index 7d52c502d1..0b7ae3aa4f 100644 --- a/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-unicoil-noexp.md +++ b/docs/regressions/regressions-beir-v1.0.0-webis-touche2020-unicoil-noexp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/beir-v1.0.0-webis-touche2020-unicoil-noexp \ - -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-unicoil-noexp/ \ -threads 16 -impact -pretokenized \ >& logs/log.beir-v1.0.0-webis-touche2020-unicoil-noexp & ``` @@ -42,7 +42,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.beir-v1.0.0-webis-touche2020-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.beir-v1.0.0-webis-touche2020.test.unicoil-noexp.tsv.gz \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.beir-v1.0.0-webis-touche2020-unicoil-noexp.unicoil-noexp.topics.beir-v1.0.0-webis-touche2020.test.unicoil-noexp.txt \ -impact -pretokenized -removeQuery -hits 1000 & ``` diff --git a/docs/regressions/regressions-car17v1.5.md b/docs/regressions/regressions-car17v1.5.md index 4633706b39..1c2559ed94 100644 --- a/docs/regressions/regressions-car17v1.5.md +++ b/docs/regressions/regressions-car17v1.5.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection CarCollection \ -input /path/to/car-paragraphCorpus.v1.5 \ - -index indexes/lucene-index.car-paragraphCorpus.v1.5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.car-paragraphCorpus.v1.5/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.car-paragraphCorpus.v1.5 & ``` @@ -46,42 +46,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v1.5/ \ -topics tools/topics-and-qrels/topics.car17v1.5.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v1.5.bm25.topics.car17v1.5.benchmarkY1test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v1.5/ \ -topics tools/topics-and-qrels/topics.car17v1.5.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v1.5.bm25+rm3.topics.car17v1.5.benchmarkY1test.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v1.5/ \ -topics tools/topics-and-qrels/topics.car17v1.5.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v1.5.bm25+ax.topics.car17v1.5.benchmarkY1test.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v1.5/ \ -topics tools/topics-and-qrels/topics.car17v1.5.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v1.5.ql.topics.car17v1.5.benchmarkY1test.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v1.5/ \ -topics tools/topics-and-qrels/topics.car17v1.5.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v1.5.ql+rm3.topics.car17v1.5.benchmarkY1test.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v1.5/ \ -topics tools/topics-and-qrels/topics.car17v1.5.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v1.5.ql+ax.topics.car17v1.5.benchmarkY1test.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-car17v2.0-doc2query.md b/docs/regressions/regressions-car17v2.0-doc2query.md index b72fe09967..e33cf499c1 100644 --- a/docs/regressions/regressions-car17v2.0-doc2query.md +++ b/docs/regressions/regressions-car17v2.0-doc2query.md @@ -26,8 +26,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/car-paragraphCorpus.v2.0-doc2query \ - -index indexes/lucene-index.car-paragraphCorpus.v2.0-doc2query/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.car-paragraphCorpus.v2.0-doc2query/ \ -threads 30 -storePositions -storeDocvectors -storeRaw \ >& logs/log.car-paragraphCorpus.v2.0-doc2query & ``` @@ -52,42 +52,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0-doc2query/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0-doc2query.bm25.topics.car17v2.0.benchmarkY1test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0-doc2query/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0-doc2query.bm25+rm3.topics.car17v2.0.benchmarkY1test.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0-doc2query/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0-doc2query.bm25+ax.topics.car17v2.0.benchmarkY1test.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0-doc2query/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0-doc2query.ql.topics.car17v2.0.benchmarkY1test.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0-doc2query/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0-doc2query.ql+rm3.topics.car17v2.0.benchmarkY1test.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0-doc2query/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0-doc2query.ql+ax.topics.car17v2.0.benchmarkY1test.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-car17v2.0.md b/docs/regressions/regressions-car17v2.0.md index 7bdbf8388e..132d598892 100644 --- a/docs/regressions/regressions-car17v2.0.md +++ b/docs/regressions/regressions-car17v2.0.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection CarCollection \ -input /path/to/car-paragraphCorpus.v2.0 \ - -index indexes/lucene-index.car-paragraphCorpus.v2.0/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.car-paragraphCorpus.v2.0/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.car-paragraphCorpus.v2.0 & ``` @@ -46,42 +46,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0.bm25.topics.car17v2.0.benchmarkY1test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0.bm25+rm3.topics.car17v2.0.benchmarkY1test.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0.bm25+ax.topics.car17v2.0.benchmarkY1test.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0.ql.topics.car17v2.0.benchmarkY1test.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0.ql+rm3.topics.car17v2.0.benchmarkY1test.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.car-paragraphCorpus.v2.0/ \ -topics tools/topics-and-qrels/topics.car17v2.0.benchmarkY1test.txt \ - -topicreader Car \ + -topicReader Car \ -output runs/run.car-paragraphCorpus.v2.0.ql+ax.topics.car17v2.0.benchmarkY1test.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-ciral-v1.0-ha.md b/docs/regressions/regressions-ciral-v1.0-ha.md index 09e736d355..70573e1ce6 100644 --- a/docs/regressions/regressions-ciral-v1.0-ha.md +++ b/docs/regressions/regressions-ciral-v1.0-ha.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/ciral-hausa \ - -index indexes/lucene-index.ciral-v1.0-ha/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.ciral-v1.0-ha/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language ha \ >& logs/log.ciral-hausa & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.ciral-v1.0-ha/ \ -topics tools/topics-and-qrels/topics.ciral-v1.0-ha-dev-native.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.ciral-hausa.bm25-default.topics.ciral-v1.0-ha-dev-native.txt \ -bm25 -hits 1000 -language ha & ``` diff --git a/docs/regressions/regressions-ciral-v1.0-so.md b/docs/regressions/regressions-ciral-v1.0-so.md index 69d42d0b4b..29c6a5e1ad 100644 --- a/docs/regressions/regressions-ciral-v1.0-so.md +++ b/docs/regressions/regressions-ciral-v1.0-so.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/ciral-somali \ - -index indexes/lucene-index.ciral-v1.0-so/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.ciral-v1.0-so/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language so \ >& logs/log.ciral-somali & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.ciral-v1.0-so/ \ -topics tools/topics-and-qrels/topics.ciral-v1.0-so-dev-native.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.ciral-somali.bm25-default.topics.ciral-v1.0-so-dev-native.txt \ -bm25 -hits 1000 -language so & ``` diff --git a/docs/regressions/regressions-ciral-v1.0-sw.md b/docs/regressions/regressions-ciral-v1.0-sw.md index 6b510c915b..e231028362 100644 --- a/docs/regressions/regressions-ciral-v1.0-sw.md +++ b/docs/regressions/regressions-ciral-v1.0-sw.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/ciral-somali \ - -index indexes/lucene-index.ciral-v1.0-sw/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.ciral-v1.0-sw/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language sw \ >& logs/log.ciral-somali & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.ciral-v1.0-sw/ \ -topics tools/topics-and-qrels/topics.ciral-v1.0-sw-dev-native.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.ciral-somali.bm25-default.topics.ciral-v1.0-sw-dev-native.txt \ -bm25 -hits 1000 -language sw & ``` diff --git a/docs/regressions/regressions-ciral-v1.0-yo.md b/docs/regressions/regressions-ciral-v1.0-yo.md index 3e7653812c..3f13069d62 100644 --- a/docs/regressions/regressions-ciral-v1.0-yo.md +++ b/docs/regressions/regressions-ciral-v1.0-yo.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/ciral-yoruba \ - -index indexes/lucene-index.ciral-v1.0-yo/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.ciral-v1.0-yo/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language yo \ >& logs/log.ciral-yoruba & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.ciral-v1.0-yo/ \ -topics tools/topics-and-qrels/topics.ciral-v1.0-yo-dev-native.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.ciral-yoruba.bm25-default.topics.ciral-v1.0-yo-dev-native.txt \ -bm25 -hits 1000 -language yo & ``` diff --git a/docs/regressions/regressions-clef06-fr.md b/docs/regressions/regressions-clef06-fr.md index e660e54b00..d0983ca75d 100644 --- a/docs/regressions/regressions-clef06-fr.md +++ b/docs/regressions/regressions-clef06-fr.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/clef06-fr \ - -index indexes/lucene-index.clef06-fr/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.clef06-fr/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language fr \ >& logs/log.clef06-fr & ``` @@ -45,7 +45,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.clef06-fr/ \ -topics tools/topics-and-qrels/topics.clef06fr.mono.fr.txt \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.clef06-fr.bm25.topics.clef06fr.mono.fr.txt \ -bm25 -language fr & ``` diff --git a/docs/regressions/regressions-core17.md b/docs/regressions/regressions-core17.md index b1c3fb6865..061c651d18 100644 --- a/docs/regressions/regressions-core17.md +++ b/docs/regressions/regressions-core17.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NewYorkTimesCollection \ -input /path/to/nyt \ - -index indexes/lucene-index.nyt/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.nyt/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.nyt & ``` @@ -45,42 +45,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.nyt/ \ -topics tools/topics-and-qrels/topics.core17.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.nyt.bm25.topics.core17.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.nyt/ \ -topics tools/topics-and-qrels/topics.core17.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.nyt.bm25+rm3.topics.core17.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.nyt/ \ -topics tools/topics-and-qrels/topics.core17.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.nyt.bm25+ax.topics.core17.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.nyt/ \ -topics tools/topics-and-qrels/topics.core17.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.nyt.ql.topics.core17.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.nyt/ \ -topics tools/topics-and-qrels/topics.core17.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.nyt.ql+rm3.topics.core17.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.nyt/ \ -topics tools/topics-and-qrels/topics.core17.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.nyt.ql+ax.topics.core17.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-core18.md b/docs/regressions/regressions-core18.md index b95e0f9356..41da2f2586 100644 --- a/docs/regressions/regressions-core18.md +++ b/docs/regressions/regressions-core18.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection WashingtonPostCollection \ -input /path/to/wapo.v2 \ - -index indexes/lucene-index.wapo.v2/ \ -generator WashingtonPostGenerator \ + -index indexes/lucene-index.wapo.v2/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.wapo.v2 & ``` @@ -45,42 +45,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.core18.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wapo.v2.bm25.topics.core18.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.core18.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wapo.v2.bm25+rm3.topics.core18.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.core18.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wapo.v2.bm25+ax.topics.core18.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.core18.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wapo.v2.ql.topics.core18.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.core18.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wapo.v2.ql+rm3.topics.core18.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wapo.v2/ \ -topics tools/topics-and-qrels/topics.core18.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wapo.v2.ql+ax.topics.core18.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-cw09b.md b/docs/regressions/regressions-cw09b.md index 20517daf87..7d58239ebd 100644 --- a/docs/regressions/regressions-cw09b.md +++ b/docs/regressions/regressions-cw09b.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection ClueWeb09Collection \ -input /path/to/cw09b \ - -index indexes/lucene-index.cw09b/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.cw09b/ \ -threads 44 -storeRaw \ >& logs/log.cw09b & ``` @@ -50,114 +50,114 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.51-100.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25.topics.web.51-100.txt \ -parallelism 16 -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.101-150.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25.topics.web.101-150.txt \ -parallelism 16 -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.151-200.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25.topics.web.151-200.txt \ -parallelism 16 -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.51-100.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25+rm3.topics.web.51-100.txt \ -parallelism 16 -bm25 -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.101-150.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25+rm3.topics.web.101-150.txt \ -parallelism 16 -bm25 -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.151-200.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25+rm3.topics.web.151-200.txt \ -parallelism 16 -bm25 -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.51-100.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25+ax.topics.web.51-100.txt \ -parallelism 16 -bm25 -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.101-150.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25+ax.topics.web.101-150.txt \ -parallelism 16 -bm25 -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.151-200.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.bm25+ax.topics.web.151-200.txt \ -parallelism 16 -bm25 -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.51-100.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql.topics.web.51-100.txt \ -parallelism 16 -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.101-150.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql.topics.web.101-150.txt \ -parallelism 16 -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.151-200.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql.topics.web.151-200.txt \ -parallelism 16 -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.51-100.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql+rm3.topics.web.51-100.txt \ -parallelism 16 -qld -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.101-150.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql+rm3.topics.web.101-150.txt \ -parallelism 16 -qld -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.151-200.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql+rm3.topics.web.151-200.txt \ -parallelism 16 -qld -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.51-100.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql+ax.topics.web.51-100.txt \ -parallelism 16 -qld -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.101-150.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql+ax.topics.web.101-150.txt \ -parallelism 16 -qld -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw09b/ \ -topics tools/topics-and-qrels/topics.web.151-200.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw09b.ql+ax.topics.web.151-200.txt \ -parallelism 16 -qld -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & ``` diff --git a/docs/regressions/regressions-cw12.md b/docs/regressions/regressions-cw12.md index 526206ac83..3d7d420319 100644 --- a/docs/regressions/regressions-cw12.md +++ b/docs/regressions/regressions-cw12.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection ClueWeb12Collection \ -input /path/to/cw12 \ - -index indexes/lucene-index.cw12/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.cw12/ \ -threads 44 -storeRaw \ >& logs/log.cw12 & ``` @@ -46,52 +46,52 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12.bm25.topics.web.201-250.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12.bm25.topics.web.251-300.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12.bm25+rm3.topics.web.201-250.txt \ -parallelism 16 -bm25 -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12.bm25+rm3.topics.web.251-300.txt \ -parallelism 16 -bm25 -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12.ql.topics.web.201-250.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12.ql.topics.web.251-300.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12.ql+rm3.topics.web.201-250.txt \ -parallelism 16 -qld -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12.ql+rm3.topics.web.251-300.txt \ -parallelism 16 -qld -rm3 -collection ClueWeb09Collection & ``` diff --git a/docs/regressions/regressions-cw12b13.md b/docs/regressions/regressions-cw12b13.md index 76d010f085..004346acdd 100644 --- a/docs/regressions/regressions-cw12b13.md +++ b/docs/regressions/regressions-cw12b13.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection ClueWeb12Collection \ -input /path/to/cw12b13 \ - -index indexes/lucene-index.cw12b13/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.cw12b13/ \ -threads 44 -storeRaw \ >& logs/log.cw12b13 & ``` @@ -46,78 +46,78 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.bm25.topics.web.201-250.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.bm25.topics.web.251-300.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.bm25+rm3.topics.web.201-250.txt \ -bm25 -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.bm25+rm3.topics.web.251-300.txt \ -bm25 -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.bm25+ax.topics.web.201-250.txt \ -bm25 -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.bm25+ax.topics.web.251-300.txt \ -bm25 -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.ql.topics.web.201-250.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.ql.topics.web.251-300.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.ql+rm3.topics.web.201-250.txt \ -qld -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.ql+rm3.topics.web.251-300.txt \ -qld -rm3 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.201-250.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.ql+ax.topics.web.201-250.txt \ -qld -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.cw12b13/ \ -topics tools/topics-and-qrels/topics.web.251-300.txt \ - -topicreader Webxml \ + -topicReader Webxml \ -output runs/run.cw12b13.ql+ax.topics.web.251-300.txt \ -qld -axiom -axiom.deterministic -axiom.beta 0.1 -rerankCutoff 20 -collection ClueWeb09Collection & ``` diff --git a/docs/regressions/regressions-disk12.md b/docs/regressions/regressions-disk12.md index eba5ebb565..9fe3e4ffca 100644 --- a/docs/regressions/regressions-disk12.md +++ b/docs/regressions/regressions-disk12.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection TrecCollection \ -input /path/to/disk12 \ - -index indexes/lucene-index.disk12/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.disk12/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.disk12 & ``` @@ -48,114 +48,114 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.51-100.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25.topics.adhoc.51-100.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.101-150.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25.topics.adhoc.101-150.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.151-200.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25.topics.adhoc.151-200.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.51-100.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25+rm3.topics.adhoc.51-100.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.101-150.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25+rm3.topics.adhoc.101-150.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.151-200.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25+rm3.topics.adhoc.151-200.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.51-100.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25+ax.topics.adhoc.51-100.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.101-150.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25+ax.topics.adhoc.101-150.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.151-200.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.bm25+ax.topics.adhoc.151-200.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.51-100.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql.topics.adhoc.51-100.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.101-150.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql.topics.adhoc.101-150.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.151-200.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql.topics.adhoc.151-200.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.51-100.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql+rm3.topics.adhoc.51-100.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.101-150.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql+rm3.topics.adhoc.101-150.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.151-200.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql+rm3.topics.adhoc.151-200.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.51-100.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql+ax.topics.adhoc.51-100.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.101-150.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql+ax.topics.adhoc.101-150.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk12/ \ -topics tools/topics-and-qrels/topics.adhoc.151-200.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk12.ql+ax.topics.adhoc.151-200.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-disk45.md b/docs/regressions/regressions-disk45.md index 82e067ef9a..a59634a6b2 100644 --- a/docs/regressions/regressions-disk45.md +++ b/docs/regressions/regressions-disk45.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection TrecCollection \ -input /path/to/disk45 \ - -index indexes/lucene-index.disk45/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.disk45/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.disk45 & ``` @@ -47,190 +47,190 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25.topics.adhoc.351-400.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25.topics.adhoc.401-450.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25.topics.robust04.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rm3.topics.adhoc.351-400.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rm3.topics.adhoc.401-450.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rm3.topics.robust04.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rocchio.topics.adhoc.351-400.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rocchio.topics.adhoc.401-450.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rocchio.topics.robust04.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rocchio-neg.topics.adhoc.351-400.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rocchio-neg.topics.adhoc.401-450.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+rocchio-neg.topics.robust04.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+ax.topics.adhoc.351-400.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+ax.topics.adhoc.401-450.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.bm25+ax.topics.robust04.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql.topics.adhoc.351-400.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql.topics.adhoc.401-450.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql.topics.robust04.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql+rm3.topics.adhoc.351-400.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql+rm3.topics.adhoc.401-450.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql+rm3.topics.robust04.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.qld+rocchio.topics.adhoc.351-400.txt \ -qld -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.qld+rocchio.topics.adhoc.401-450.txt \ -qld -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.qld+rocchio.topics.robust04.txt \ -qld -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.qld+rocchio-neg.topics.adhoc.351-400.txt \ -qld -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.qld+rocchio-neg.topics.adhoc.401-450.txt \ -qld -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.qld+rocchio-neg.topics.robust04.txt \ -qld -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.351-400.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql+ax.topics.adhoc.351-400.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.adhoc.401-450.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql+ax.topics.adhoc.401-450.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.disk45/ \ -topics tools/topics-and-qrels/topics.robust04.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.disk45.ql+ax.topics.robust04.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-dl19-doc-ca.md b/docs/regressions/regressions-dl19-doc-ca.md index 3e6a52a3f9..da6dba1e64 100644 --- a/docs/regressions/regressions-dl19-doc-ca.md +++ b/docs/regressions/regressions-dl19-doc-ca.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc \ - -index indexes/lucene-index.msmarco-doc-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-ca/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-doc & ``` @@ -47,7 +47,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-ca/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default.topics.dl19-doc.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-dl19-doc-docTTTTTquery.md b/docs/regressions/regressions-dl19-doc-docTTTTTquery.md index b32671e48d..9d1260e7a8 100644 --- a/docs/regressions/regressions-dl19-doc-docTTTTTquery.md +++ b/docs/regressions/regressions-dl19-doc-docTTTTTquery.md @@ -35,8 +35,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-docTTTTTquery \ - -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -threads 7 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-docTTTTTquery & ``` @@ -58,42 +58,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-default.topics.dl19-doc.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-default+rm3.topics.dl19-doc.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-default+rocchio.topics.dl19-doc.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-tuned.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.68 -bm25.b 0.87 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-tuned+rm3.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.68 -bm25.b 0.87 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-tuned+rocchio.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.68 -bm25.b 0.87 -rocchio & ``` diff --git a/docs/regressions/regressions-dl19-doc-hgf-wp.md b/docs/regressions/regressions-dl19-doc-hgf-wp.md index a6ef83bdc7..965664ebec 100644 --- a/docs/regressions/regressions-dl19-doc-hgf-wp.md +++ b/docs/regressions/regressions-dl19-doc-hgf-wp.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc \ - -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -threads 7 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased \ >& logs/log.msmarco-doc & ``` @@ -48,7 +48,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default.topics.dl19-doc.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased & ``` diff --git a/docs/regressions/regressions-dl19-doc-segmented-ca.md b/docs/regressions/regressions-dl19-doc-segmented-ca.md index e79d1eef6b..0a54f97d39 100644 --- a/docs/regressions/regressions-dl19-doc-segmented-ca.md +++ b/docs/regressions/regressions-dl19-doc-segmented-ca.md @@ -33,8 +33,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented \ - -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-doc-segmented & ``` @@ -56,7 +56,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default.topics.dl19-doc.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-dl19-doc-segmented-docTTTTTquery.md b/docs/regressions/regressions-dl19-doc-segmented-docTTTTTquery.md index 370a2cd530..22fd661486 100644 --- a/docs/regressions/regressions-dl19-doc-segmented-docTTTTTquery.md +++ b/docs/regressions/regressions-dl19-doc-segmented-docTTTTTquery.md @@ -36,8 +36,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented-docTTTTTquery \ - -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-segmented-docTTTTTquery & ``` @@ -59,42 +59,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-default.topics.dl19-doc.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-default+rm3.topics.dl19-doc.txt \ -bm25 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-default+rocchio.topics.dl19-doc.txt \ -bm25 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-tuned.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.56 -bm25.b 0.59 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-tuned+rm3.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.56 -bm25.b 0.59 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-tuned+rocchio.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.56 -bm25.b 0.59 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl19-doc-segmented-unicoil-noexp.md b/docs/regressions/regressions-dl19-doc-segmented-unicoil-noexp.md index 725f33afbe..9fe22f4214 100644 --- a/docs/regressions/regressions-dl19-doc-segmented-unicoil-noexp.md +++ b/docs/regressions/regressions-dl19-doc-segmented-unicoil-noexp.md @@ -56,8 +56,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-doc-segmented-unicoil-noexp \ - -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-doc-segmented-unicoil-noexp & ``` @@ -81,21 +81,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl19-doc.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil-noexp.unicoil.topics.dl19-doc.unicoil-noexp.0shot.txt \ -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl19-doc.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil-noexp.rm3.topics.dl19-doc.unicoil-noexp.0shot.txt \ -impact -pretokenized -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl19-doc.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil-noexp.rocchio.topics.dl19-doc.unicoil-noexp.0shot.txt \ -impact -pretokenized -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl19-doc-segmented-unicoil.md b/docs/regressions/regressions-dl19-doc-segmented-unicoil.md index 01cef7c44f..a5aa85b6f7 100644 --- a/docs/regressions/regressions-dl19-doc-segmented-unicoil.md +++ b/docs/regressions/regressions-dl19-doc-segmented-unicoil.md @@ -56,8 +56,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-doc-segmented-unicoil \ - -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-doc-segmented-unicoil & ``` @@ -81,21 +81,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -topics tools/topics-and-qrels/topics.dl19-doc.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil.unicoil.topics.dl19-doc.unicoil.0shot.txt \ -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -topics tools/topics-and-qrels/topics.dl19-doc.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil.rm3.topics.dl19-doc.unicoil.0shot.txt \ -impact -pretokenized -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -topics tools/topics-and-qrels/topics.dl19-doc.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil.rocchio.topics.dl19-doc.unicoil.0shot.txt \ -impact -pretokenized -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl19-doc-segmented-wp.md b/docs/regressions/regressions-dl19-doc-segmented-wp.md index fd923b8794..cb1b61b8df 100644 --- a/docs/regressions/regressions-dl19-doc-segmented-wp.md +++ b/docs/regressions/regressions-dl19-doc-segmented-wp.md @@ -26,8 +26,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented-wp \ - -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-doc-segmented-wp & ``` @@ -49,7 +49,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -topics tools/topics-and-qrels/topics.dl19-doc.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-wp.bm25-default.topics.dl19-doc.wp.txt \ -bm25 -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl19-doc-segmented.md b/docs/regressions/regressions-dl19-doc-segmented.md index e09a6d8828..504b7b0929 100644 --- a/docs/regressions/regressions-dl19-doc-segmented.md +++ b/docs/regressions/regressions-dl19-doc-segmented.md @@ -36,8 +36,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented \ - -index indexes/lucene-index.msmarco-doc-segmented/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-segmented & ``` @@ -59,84 +59,84 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default.topics.dl19-doc.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+rm3.topics.dl19-doc.txt \ -bm25 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+rocchio.topics.dl19-doc.txt \ -bm25 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+rocchio-neg.topics.dl19-doc.txt \ -bm25 -rocchio -rocchio.useNegative -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+ax.topics.dl19-doc.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+prf.topics.dl19-doc.txt \ -bm25 -bm25prf -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+rm3.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+rocchio.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+rocchio-neg.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rocchio -rocchio.useNegative -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+ax.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -axiom -axiom.deterministic -rerankCutoff 20 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+prf.topics.dl19-doc.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -bm25prf -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl19-doc-wp.md b/docs/regressions/regressions-dl19-doc-wp.md index f3f810f8db..16ea3109d0 100644 --- a/docs/regressions/regressions-dl19-doc-wp.md +++ b/docs/regressions/regressions-dl19-doc-wp.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-wp \ - -index indexes/lucene-index.msmarco-doc-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-wp/ \ -threads 7 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-doc-wp & ``` @@ -48,7 +48,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-wp/ \ -topics tools/topics-and-qrels/topics.dl19-doc.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-wp.bm25-default.topics.dl19-doc.wp.txt \ -bm25 -pretokenized & ``` diff --git a/docs/regressions/regressions-dl19-doc.md b/docs/regressions/regressions-dl19-doc.md index ab0f36b364..68f9b41197 100644 --- a/docs/regressions/regressions-dl19-doc.md +++ b/docs/regressions/regressions-dl19-doc.md @@ -35,8 +35,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc \ - -index indexes/lucene-index.msmarco-doc/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc/ \ -threads 7 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc & ``` @@ -58,126 +58,126 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default.topics.dl19-doc.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default+rm3.topics.dl19-doc.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default+rocchio.topics.dl19-doc.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default+rocchio-neg.topics.dl19-doc.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default+ax.topics.dl19-doc.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default+prf.topics.dl19-doc.txt \ -bm25 -bm25prf & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned.topics.dl19-doc.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned+rm3.topics.dl19-doc.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned+rocchio.topics.dl19-doc.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned+rocchio-neg.topics.dl19-doc.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned+ax.topics.dl19-doc.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned+prf.topics.dl19-doc.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -bm25prf & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned2.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned2+rm3.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned2+rocchio.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned2+rocchio-neg.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned2+ax.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl19-doc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned2+prf.topics.dl19-doc.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -bm25prf & ``` diff --git a/docs/regressions/regressions-dl19-passage-bm25-b8.md b/docs/regressions/regressions-dl19-passage-bm25-b8.md index 725bff5f76..cde1cd62d4 100644 --- a/docs/regressions/regressions-dl19-passage-bm25-b8.md +++ b/docs/regressions/regressions-dl19-passage-bm25-b8.md @@ -49,8 +49,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-bm25-b8 \ - -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -threads 9 -impact -pretokenized \ >& logs/log.msmarco-passage-bm25-b8 & ``` @@ -71,7 +71,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-bm25-b8.bm25-b8.topics.dl19-passage.txt \ -impact & ``` diff --git a/docs/regressions/regressions-dl19-passage-ca.md b/docs/regressions/regressions-dl19-passage-ca.md index 541a0b22e1..a3747d7280 100644 --- a/docs/regressions/regressions-dl19-passage-ca.md +++ b/docs/regressions/regressions-dl19-passage-ca.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage \ - -index indexes/lucene-index.msmarco-passage-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-ca/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-passage & ``` @@ -47,7 +47,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-ca/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default.topics.dl19-passage.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-dl19-passage-cos-dpr-distil-fw.md b/docs/regressions/regressions-dl19-passage-cos-dpr-distil-fw.md index b355cfba42..8a2e0884f0 100644 --- a/docs/regressions/regressions-dl19-passage-cos-dpr-distil-fw.md +++ b/docs/regressions/regressions-dl19-passage-cos-dpr-distil-fw.md @@ -52,8 +52,8 @@ Sample indexing command, applying inverted indexes to dense vectors using the "f target/appassembler/bin/IndexInvertedDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ - -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -generator InvertedDenseVectorDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -threads 16 -encoding fw -fw.q 40 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -74,9 +74,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchInvertedDenseVectors \ -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -topics tools/topics-and-qrels/topics.dl19-passage.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-fw-40.topics.dl19-passage.cos-dpr-distil.jsonl.txt \ - -topicfield vector -encoding fw -fw.q 40 -hits 1000 & + -topicField vector -encoding fw -fw.q 40 -hits 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl19-passage-cos-dpr-distil-hnsw-onnx.md b/docs/regressions/regressions-dl19-passage-cos-dpr-distil-hnsw-onnx.md index d68a6c8754..e98ee2e74e 100644 --- a/docs/regressions/regressions-dl19-passage-cos-dpr-distil-hnsw-onnx.md +++ b/docs/regressions/regressions-dl19-passage-cos-dpr-distil-hnsw-onnx.md @@ -55,8 +55,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -77,9 +77,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-hnsw.topics.dl19-passage.txt \ - -querygenerator VectorQueryGenerator -topicfield title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil & + -generator VectorQueryGenerator -topicField title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl19-passage-cos-dpr-distil-hnsw.md b/docs/regressions/regressions-dl19-passage-cos-dpr-distil-hnsw.md index c86f607c0a..aed4b16719 100644 --- a/docs/regressions/regressions-dl19-passage-cos-dpr-distil-hnsw.md +++ b/docs/regressions/regressions-dl19-passage-cos-dpr-distil-hnsw.md @@ -55,8 +55,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -77,9 +77,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-hnsw.topics.dl19-passage.cos-dpr-distil.jsonl.txt \ - -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 & + -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl19-passage-cos-dpr-distil-lexlsh.md b/docs/regressions/regressions-dl19-passage-cos-dpr-distil-lexlsh.md index 8e4431311e..83ee16cd3f 100644 --- a/docs/regressions/regressions-dl19-passage-cos-dpr-distil-lexlsh.md +++ b/docs/regressions/regressions-dl19-passage-cos-dpr-distil-lexlsh.md @@ -52,8 +52,8 @@ Sample indexing command, applying inverted indexes to dense vectors using the "L target/appassembler/bin/IndexInvertedDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ - -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -generator InvertedDenseVectorDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -threads 16 -encoding lexlsh -lexlsh.b 600 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -74,9 +74,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchInvertedDenseVectors \ -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -topics tools/topics-and-qrels/topics.dl19-passage.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-lexlsh-600.topics.dl19-passage.cos-dpr-distil.jsonl.txt \ - -topicfield vector -encoding lexlsh -lexlsh.b 600 -hits 1000 & + -topicField vector -encoding lexlsh -lexlsh.b 600 -hits 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl19-passage-docTTTTTquery.md b/docs/regressions/regressions-dl19-passage-docTTTTTquery.md index acd70039b9..db3e649cf2 100644 --- a/docs/regressions/regressions-dl19-passage-docTTTTTquery.md +++ b/docs/regressions/regressions-dl19-passage-docTTTTTquery.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage-docTTTTTquery \ - -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -threads 9 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-passage-docTTTTTquery & ``` @@ -48,84 +48,84 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default.topics.dl19-passage.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default+rm3.topics.dl19-passage.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default+rocchio.topics.dl19-passage.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default+rocchio-neg.topics.dl19-passage.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned+rm3.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned+rocchio.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned+rocchio-neg.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2.topics.dl19-passage.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2+rm3.topics.dl19-passage.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2+rocchio.topics.dl19-passage.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2+rocchio-neg.topics.dl19-passage.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 -rocchio -rocchio.useNegative -rerankCutoff 1000 & ``` diff --git a/docs/regressions/regressions-dl19-passage-hgf-wp.md b/docs/regressions/regressions-dl19-passage-hgf-wp.md index 4c406e9507..bd5cf82d58 100644 --- a/docs/regressions/regressions-dl19-passage-hgf-wp.md +++ b/docs/regressions/regressions-dl19-passage-hgf-wp.md @@ -26,8 +26,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage \ - -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased \ >& logs/log.msmarco-passage & ``` @@ -48,7 +48,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default.topics.dl19-passage.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased & ``` diff --git a/docs/regressions/regressions-dl19-passage-openai-ada2.md b/docs/regressions/regressions-dl19-passage-openai-ada2.md index d096a4796b..cecd54ea8e 100644 --- a/docs/regressions/regressions-dl19-passage-openai-ada2.md +++ b/docs/regressions/regressions-dl19-passage-openai-ada2.md @@ -55,8 +55,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-openai-ada2/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 -memorybuffer 65536 \ >& logs/log.msmarco-passage-openai-ada2 & ``` @@ -77,9 +77,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-openai-ada2/ \ -topics tools/topics-and-qrels/topics.dl19-passage.openai-ada2.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-openai-ada2.openai-ada2.topics.dl19-passage.openai-ada2.jsonl.txt \ - -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 & + -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl19-passage-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-dl19-passage-splade-distil-cocodenser-medium.md index 7ea6c155bc..4c31a3025e 100644 --- a/docs/regressions/regressions-dl19-passage-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-dl19-passage-splade-distil-cocodenser-medium.md @@ -54,8 +54,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade_distil_cocodenser_medium & ``` @@ -79,21 +79,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.dl19-passage.splade_distil_cocodenser_medium.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade_distil_cocodenser_medium.rm3.topics.dl19-passage.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade_distil_cocodenser_medium.rocchio.topics.dl19-passage.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl19-passage-splade-pp-ed-onnx.md b/docs/regressions/regressions-dl19-passage-splade-pp-ed-onnx.md index a7a27079ee..4d373aad15 100644 --- a/docs/regressions/regressions-dl19-passage-splade-pp-ed-onnx.md +++ b/docs/regressions/regressions-dl19-passage-splade-pp-ed-onnx.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-ed & ``` @@ -80,21 +80,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.splade-pp-ed.topics.dl19-passage.txt \ -impact -pretokenized -encoder SpladePlusPlusEnsembleDistil & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.rm3.topics.dl19-passage.txt \ -impact -pretokenized -encoder SpladePlusPlusEnsembleDistil -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.rocchio.topics.dl19-passage.txt \ -impact -pretokenized -encoder SpladePlusPlusEnsembleDistil -rocchio & ``` diff --git a/docs/regressions/regressions-dl19-passage-splade-pp-ed.md b/docs/regressions/regressions-dl19-passage-splade-pp-ed.md index 56ad9a325c..32677d6a85 100644 --- a/docs/regressions/regressions-dl19-passage-splade-pp-ed.md +++ b/docs/regressions/regressions-dl19-passage-splade-pp-ed.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-ed & ``` @@ -80,21 +80,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.splade-pp-ed.topics.dl19-passage.splade-pp-ed.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.rm3.topics.dl19-passage.splade-pp-ed.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.rocchio.topics.dl19-passage.splade-pp-ed.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl19-passage-splade-pp-sd-onnx.md b/docs/regressions/regressions-dl19-passage-splade-pp-sd-onnx.md index 4e2212a4dc..1ca6f43974 100644 --- a/docs/regressions/regressions-dl19-passage-splade-pp-sd-onnx.md +++ b/docs/regressions/regressions-dl19-passage-splade-pp-sd-onnx.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-sd & ``` @@ -80,21 +80,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.splade-pp-sd.topics.dl19-passage.txt \ -impact -pretokenized -encoder SpladePlusPlusSelfDistil & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.rm3.topics.dl19-passage.txt \ -impact -pretokenized -rm3 -encoder SpladePlusPlusSelfDistil & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.rocchio.topics.dl19-passage.txt \ -impact -pretokenized -rocchio -encoder SpladePlusPlusSelfDistil & ``` diff --git a/docs/regressions/regressions-dl19-passage-splade-pp-sd.md b/docs/regressions/regressions-dl19-passage-splade-pp-sd.md index 4a6e7b53bb..483fc41e82 100644 --- a/docs/regressions/regressions-dl19-passage-splade-pp-sd.md +++ b/docs/regressions/regressions-dl19-passage-splade-pp-sd.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-sd & ``` @@ -80,21 +80,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.splade-pp-sd.topics.dl19-passage.splade-pp-sd.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.rm3.topics.dl19-passage.splade-pp-sd.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl19-passage.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.rocchio.topics.dl19-passage.splade-pp-sd.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl19-passage-unicoil-noexp.md b/docs/regressions/regressions-dl19-passage-unicoil-noexp.md index 5d2fb2c3d5..9ee9835cc3 100644 --- a/docs/regressions/regressions-dl19-passage-unicoil-noexp.md +++ b/docs/regressions/regressions-dl19-passage-unicoil-noexp.md @@ -58,8 +58,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-unicoil-noexp \ - -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-unicoil-noexp & ``` @@ -83,21 +83,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl19-passage.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil-noexp.unicoil.topics.dl19-passage.unicoil-noexp.0shot.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl19-passage.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil-noexp.rm3.topics.dl19-passage.unicoil-noexp.0shot.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl19-passage.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil-noexp.rocchio.topics.dl19-passage.unicoil-noexp.0shot.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl19-passage-unicoil.md b/docs/regressions/regressions-dl19-passage-unicoil.md index 4e8060a570..4c8bb80118 100644 --- a/docs/regressions/regressions-dl19-passage-unicoil.md +++ b/docs/regressions/regressions-dl19-passage-unicoil.md @@ -58,8 +58,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-unicoil \ - -index indexes/lucene-index.msmarco-passage-unicoil/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-unicoil/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-unicoil & ``` @@ -83,21 +83,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil.unicoil.topics.dl19-passage.unicoil.0shot.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil.rm3.topics.dl19-passage.unicoil.0shot.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil/ \ -topics tools/topics-and-qrels/topics.dl19-passage.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil.rocchio.topics.dl19-passage.unicoil.0shot.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl19-passage-wp.md b/docs/regressions/regressions-dl19-passage-wp.md index 0314ae06be..1b6e607304 100644 --- a/docs/regressions/regressions-dl19-passage-wp.md +++ b/docs/regressions/regressions-dl19-passage-wp.md @@ -26,8 +26,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage-wp \ - -index indexes/lucene-index.msmarco-passage-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-wp/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-passage-wp & ``` @@ -48,7 +48,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-wp/ \ -topics tools/topics-and-qrels/topics.dl19-passage.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-wp.bm25-default.topics.dl19-passage.wp.txt \ -bm25 -pretokenized & ``` diff --git a/docs/regressions/regressions-dl19-passage.md b/docs/regressions/regressions-dl19-passage.md index c21e03610e..81f277de94 100644 --- a/docs/regressions/regressions-dl19-passage.md +++ b/docs/regressions/regressions-dl19-passage.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage \ - -index indexes/lucene-index.msmarco-passage/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage/ \ -threads 9 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-passage & ``` @@ -47,84 +47,84 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default.topics.dl19-passage.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+rm3.topics.dl19-passage.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+rocchio.topics.dl19-passage.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+rocchio-neg.topics.dl19-passage.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+ax.topics.dl19-passage.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+prf.topics.dl19-passage.txt \ -bm25 -bm25prf & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+rm3.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+rocchio.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+rocchio-neg.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+ax.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl19-passage.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+prf.topics.dl19-passage.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -bm25prf & ``` diff --git a/docs/regressions/regressions-dl20-doc-ca.md b/docs/regressions/regressions-dl20-doc-ca.md index 31193f5979..cecd5c4472 100644 --- a/docs/regressions/regressions-dl20-doc-ca.md +++ b/docs/regressions/regressions-dl20-doc-ca.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc \ - -index indexes/lucene-index.msmarco-doc-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-ca/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-doc & ``` @@ -47,7 +47,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-ca/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default.topics.dl20.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-dl20-doc-docTTTTTquery.md b/docs/regressions/regressions-dl20-doc-docTTTTTquery.md index 70b7c4549a..95de25d87e 100644 --- a/docs/regressions/regressions-dl20-doc-docTTTTTquery.md +++ b/docs/regressions/regressions-dl20-doc-docTTTTTquery.md @@ -35,8 +35,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-docTTTTTquery \ - -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -threads 7 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-docTTTTTquery & ``` @@ -58,42 +58,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-default.topics.dl20.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-default+rm3.topics.dl20.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-default+rocchio.topics.dl20.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-tuned.topics.dl20.txt \ -bm25 -bm25.k1 4.68 -bm25.b 0.87 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-tuned+rm3.topics.dl20.txt \ -bm25 -bm25.k1 4.68 -bm25.b 0.87 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-tuned+rocchio.topics.dl20.txt \ -bm25 -bm25.k1 4.68 -bm25.b 0.87 -rocchio & ``` diff --git a/docs/regressions/regressions-dl20-doc-hgf-wp.md b/docs/regressions/regressions-dl20-doc-hgf-wp.md index fc95b3a49e..123ac99f26 100644 --- a/docs/regressions/regressions-dl20-doc-hgf-wp.md +++ b/docs/regressions/regressions-dl20-doc-hgf-wp.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc \ - -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -threads 7 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased \ >& logs/log.msmarco-doc & ``` @@ -48,7 +48,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default.topics.dl20.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased & ``` diff --git a/docs/regressions/regressions-dl20-doc-segmented-ca.md b/docs/regressions/regressions-dl20-doc-segmented-ca.md index a9abf540f9..8c0ce75a85 100644 --- a/docs/regressions/regressions-dl20-doc-segmented-ca.md +++ b/docs/regressions/regressions-dl20-doc-segmented-ca.md @@ -33,8 +33,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented \ - -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-doc-segmented & ``` @@ -56,7 +56,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default.topics.dl20.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-dl20-doc-segmented-docTTTTTquery.md b/docs/regressions/regressions-dl20-doc-segmented-docTTTTTquery.md index fed3dd6dff..dedcdd5413 100644 --- a/docs/regressions/regressions-dl20-doc-segmented-docTTTTTquery.md +++ b/docs/regressions/regressions-dl20-doc-segmented-docTTTTTquery.md @@ -36,8 +36,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented-docTTTTTquery \ - -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-segmented-docTTTTTquery & ``` @@ -59,42 +59,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-default.topics.dl20.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-default+rm3.topics.dl20.txt \ -bm25 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-default+rocchio.topics.dl20.txt \ -bm25 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-tuned.topics.dl20.txt \ -bm25 -bm25.k1 2.56 -bm25.b 0.59 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-tuned+rm3.topics.dl20.txt \ -bm25 -bm25.k1 2.56 -bm25.b 0.59 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-tuned+rocchio.topics.dl20.txt \ -bm25 -bm25.k1 2.56 -bm25.b 0.59 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl20-doc-segmented-unicoil-noexp.md b/docs/regressions/regressions-dl20-doc-segmented-unicoil-noexp.md index 065eb12c6c..7e1532c5dd 100644 --- a/docs/regressions/regressions-dl20-doc-segmented-unicoil-noexp.md +++ b/docs/regressions/regressions-dl20-doc-segmented-unicoil-noexp.md @@ -56,8 +56,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-doc-segmented-unicoil-noexp \ - -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-doc-segmented-unicoil-noexp & ``` @@ -81,21 +81,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil-noexp.unicoil.topics.dl20.unicoil-noexp.0shot.txt \ -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil-noexp.rm3.topics.dl20.unicoil-noexp.0shot.txt \ -impact -pretokenized -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil-noexp.rocchio.topics.dl20.unicoil-noexp.0shot.txt \ -impact -pretokenized -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl20-doc-segmented-unicoil.md b/docs/regressions/regressions-dl20-doc-segmented-unicoil.md index bb659d7b73..be68da27e9 100644 --- a/docs/regressions/regressions-dl20-doc-segmented-unicoil.md +++ b/docs/regressions/regressions-dl20-doc-segmented-unicoil.md @@ -56,8 +56,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-doc-segmented-unicoil \ - -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-doc-segmented-unicoil & ``` @@ -81,21 +81,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil.unicoil.topics.dl20.unicoil.0shot.txt \ -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil.rm3.topics.dl20.unicoil.0shot.txt \ -impact -pretokenized -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil.rocchio.topics.dl20.unicoil.0shot.txt \ -impact -pretokenized -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl20-doc-segmented-wp.md b/docs/regressions/regressions-dl20-doc-segmented-wp.md index 93dcb4181d..50e76751b6 100644 --- a/docs/regressions/regressions-dl20-doc-segmented-wp.md +++ b/docs/regressions/regressions-dl20-doc-segmented-wp.md @@ -26,8 +26,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented-wp \ - -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-doc-segmented-wp & ``` @@ -49,7 +49,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -topics tools/topics-and-qrels/topics.dl20.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-wp.bm25-default.topics.dl20.wp.txt \ -bm25 -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl20-doc-segmented.md b/docs/regressions/regressions-dl20-doc-segmented.md index fd5419c46b..8816d46396 100644 --- a/docs/regressions/regressions-dl20-doc-segmented.md +++ b/docs/regressions/regressions-dl20-doc-segmented.md @@ -36,8 +36,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented \ - -index indexes/lucene-index.msmarco-doc-segmented/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-segmented & ``` @@ -59,84 +59,84 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default.topics.dl20.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+rm3.topics.dl20.txt \ -bm25 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+rocchio.topics.dl20.txt \ -bm25 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+rocchio-neg.topics.dl20.txt \ -bm25 -rocchio -rocchio.useNegative -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+ax.topics.dl20.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default+prf.topics.dl20.txt \ -bm25 -bm25prf -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned.topics.dl20.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+rm3.topics.dl20.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rm3 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+rocchio.topics.dl20.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rocchio -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+rocchio-neg.topics.dl20.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -rocchio -rocchio.useNegative -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+ax.topics.dl20.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -axiom -axiom.deterministic -rerankCutoff 20 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned+prf.topics.dl20.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -bm25prf -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl20-doc-wp.md b/docs/regressions/regressions-dl20-doc-wp.md index 0099a067c0..9d57c78b63 100644 --- a/docs/regressions/regressions-dl20-doc-wp.md +++ b/docs/regressions/regressions-dl20-doc-wp.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-wp \ - -index indexes/lucene-index.msmarco-doc-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-wp/ \ -threads 7 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-doc-wp & ``` @@ -48,7 +48,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-wp/ \ -topics tools/topics-and-qrels/topics.dl20.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-wp.bm25-default.topics.dl20.wp.txt \ -bm25 -pretokenized & ``` diff --git a/docs/regressions/regressions-dl20-doc.md b/docs/regressions/regressions-dl20-doc.md index bd78024568..dfe07d5b09 100644 --- a/docs/regressions/regressions-dl20-doc.md +++ b/docs/regressions/regressions-dl20-doc.md @@ -35,8 +35,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmacro-doc \ - -index indexes/lucene-index.msmarco-doc/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc/ \ -threads 7 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmacro-doc & ``` @@ -58,126 +58,126 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-default.topics.dl20.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-default+rm3.topics.dl20.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-default+rocchio.topics.dl20.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-default+rocchio-neg.topics.dl20.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-default+ax.topics.dl20.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-default+prf.topics.dl20.txt \ -bm25 -bm25prf & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned.topics.dl20.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned+rm3.topics.dl20.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned+rocchio.topics.dl20.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned+rocchio-neg.topics.dl20.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned+ax.topics.dl20.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned+prf.topics.dl20.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 -bm25prf & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned2.topics.dl20.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned2+rm3.topics.dl20.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned2+rocchio.topics.dl20.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned2+rocchio-neg.topics.dl20.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned2+ax.topics.dl20.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmacro-doc.bm25-tuned2+prf.topics.dl20.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 -bm25prf & ``` diff --git a/docs/regressions/regressions-dl20-passage-bm25-b8.md b/docs/regressions/regressions-dl20-passage-bm25-b8.md index 932179c406..df6290acb5 100644 --- a/docs/regressions/regressions-dl20-passage-bm25-b8.md +++ b/docs/regressions/regressions-dl20-passage-bm25-b8.md @@ -49,8 +49,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-bm25-b8 \ - -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -threads 9 -impact -pretokenized \ >& logs/log.msmarco-passage-bm25-b8 & ``` @@ -71,7 +71,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-bm25-b8.bm25-b8.topics.dl20.txt \ -impact & ``` diff --git a/docs/regressions/regressions-dl20-passage-ca.md b/docs/regressions/regressions-dl20-passage-ca.md index f4cfb12404..a4382296d1 100644 --- a/docs/regressions/regressions-dl20-passage-ca.md +++ b/docs/regressions/regressions-dl20-passage-ca.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage \ - -index indexes/lucene-index.msmarco-passage-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-ca/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-passage & ``` @@ -47,7 +47,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-ca/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default.topics.dl20.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-dl20-passage-cos-dpr-distil-fw.md b/docs/regressions/regressions-dl20-passage-cos-dpr-distil-fw.md index 1b165bcdfc..ea330d6b7e 100644 --- a/docs/regressions/regressions-dl20-passage-cos-dpr-distil-fw.md +++ b/docs/regressions/regressions-dl20-passage-cos-dpr-distil-fw.md @@ -52,8 +52,8 @@ Sample indexing command, applying inverted indexes to dense vectors using the "f target/appassembler/bin/IndexInvertedDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ - -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -generator InvertedDenseVectorDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -threads 16 -encoding fw -fw.q 40 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -74,9 +74,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchInvertedDenseVectors \ -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -topics tools/topics-and-qrels/topics.dl20.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-fw-40.topics.dl20.cos-dpr-distil.jsonl.txt \ - -topicfield vector -encoding fw -fw.q 40 -hits 1000 & + -topicField vector -encoding fw -fw.q 40 -hits 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl20-passage-cos-dpr-distil-hnsw-onnx.md b/docs/regressions/regressions-dl20-passage-cos-dpr-distil-hnsw-onnx.md index 3230dd9f27..045417dab5 100644 --- a/docs/regressions/regressions-dl20-passage-cos-dpr-distil-hnsw-onnx.md +++ b/docs/regressions/regressions-dl20-passage-cos-dpr-distil-hnsw-onnx.md @@ -55,8 +55,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -77,9 +77,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-hnsw.topics.dl20.txt \ - -querygenerator VectorQueryGenerator -topicfield title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil & + -generator VectorQueryGenerator -topicField title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl20-passage-cos-dpr-distil-hnsw.md b/docs/regressions/regressions-dl20-passage-cos-dpr-distil-hnsw.md index 64196afc58..7408687a8c 100644 --- a/docs/regressions/regressions-dl20-passage-cos-dpr-distil-hnsw.md +++ b/docs/regressions/regressions-dl20-passage-cos-dpr-distil-hnsw.md @@ -55,8 +55,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -77,9 +77,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.dl20.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-hnsw.topics.dl20.cos-dpr-distil.jsonl.txt \ - -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 & + -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl20-passage-cos-dpr-distil-lexlsh.md b/docs/regressions/regressions-dl20-passage-cos-dpr-distil-lexlsh.md index e2777b4798..ca045b0fb4 100644 --- a/docs/regressions/regressions-dl20-passage-cos-dpr-distil-lexlsh.md +++ b/docs/regressions/regressions-dl20-passage-cos-dpr-distil-lexlsh.md @@ -52,8 +52,8 @@ Sample indexing command, applying inverted indexes to dense vectors using the "L target/appassembler/bin/IndexInvertedDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ - -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -generator InvertedDenseVectorDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -threads 16 -encoding lexlsh -lexlsh.b 600 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -74,9 +74,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchInvertedDenseVectors \ -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -topics tools/topics-and-qrels/topics.dl20.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-lexlsh-600.topics.dl20.cos-dpr-distil.jsonl.txt \ - -topicfield vector -encoding lexlsh -lexlsh.b 600 -hits 1000 & + -topicField vector -encoding lexlsh -lexlsh.b 600 -hits 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl20-passage-docTTTTTquery.md b/docs/regressions/regressions-dl20-passage-docTTTTTquery.md index b81fc19317..1ecd9ddb78 100644 --- a/docs/regressions/regressions-dl20-passage-docTTTTTquery.md +++ b/docs/regressions/regressions-dl20-passage-docTTTTTquery.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage-docTTTTTquery \ - -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -threads 9 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-passage-docTTTTTquery & ``` @@ -48,84 +48,84 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default.topics.dl20.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default+rm3.topics.dl20.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default+rocchio.topics.dl20.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default+rocchio-neg.topics.dl20.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned+rm3.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned+rocchio.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned+rocchio-neg.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2.topics.dl20.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2+rm3.topics.dl20.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2+rocchio.topics.dl20.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2+rocchio-neg.topics.dl20.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 -rocchio -rocchio.useNegative -rerankCutoff 1000 & ``` diff --git a/docs/regressions/regressions-dl20-passage-hgf-wp.md b/docs/regressions/regressions-dl20-passage-hgf-wp.md index dc0d8e77cf..e73b6e3057 100644 --- a/docs/regressions/regressions-dl20-passage-hgf-wp.md +++ b/docs/regressions/regressions-dl20-passage-hgf-wp.md @@ -26,8 +26,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage \ - -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased \ >& logs/log.msmarco-passage & ``` @@ -48,7 +48,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default.topics.dl20.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased & ``` diff --git a/docs/regressions/regressions-dl20-passage-openai-ada2.md b/docs/regressions/regressions-dl20-passage-openai-ada2.md index 69baf82cb0..57220c1465 100644 --- a/docs/regressions/regressions-dl20-passage-openai-ada2.md +++ b/docs/regressions/regressions-dl20-passage-openai-ada2.md @@ -55,8 +55,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-openai-ada2/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 -memorybuffer 65536 \ >& logs/log.msmarco-passage-openai-ada2 & ``` @@ -77,9 +77,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-openai-ada2/ \ -topics tools/topics-and-qrels/topics.dl20-passage.openai-ada2.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-openai-ada2.openai-ada2.topics.dl20-passage.openai-ada2.jsonl.txt \ - -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 & + -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-dl20-passage-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-dl20-passage-splade-distil-cocodenser-medium.md index 78e5ea547d..69502cc843 100644 --- a/docs/regressions/regressions-dl20-passage-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-dl20-passage-splade-distil-cocodenser-medium.md @@ -54,8 +54,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade_distil_cocodenser_medium & ``` @@ -79,21 +79,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.dl20.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.dl20.splade_distil_cocodenser_medium.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.dl20.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade_distil_cocodenser_medium.rm3.topics.dl20.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.dl20.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade_distil_cocodenser_medium.rocchio.topics.dl20.splade_distil_cocodenser_medium.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl20-passage-splade-pp-ed-onnx.md b/docs/regressions/regressions-dl20-passage-splade-pp-ed-onnx.md index ad239b07f0..a69fe19309 100644 --- a/docs/regressions/regressions-dl20-passage-splade-pp-ed-onnx.md +++ b/docs/regressions/regressions-dl20-passage-splade-pp-ed-onnx.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-ed & ``` @@ -80,21 +80,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.splade-pp-ed.topics.dl20.txt \ -impact -pretokenized -encoder SpladePlusPlusEnsembleDistil & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.rm3.topics.dl20.txt \ -impact -pretokenized -rm3 -encoder SpladePlusPlusEnsembleDistil & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.rocchio.topics.dl20.txt \ -impact -pretokenized -rocchio -encoder SpladePlusPlusEnsembleDistil & ``` diff --git a/docs/regressions/regressions-dl20-passage-splade-pp-ed.md b/docs/regressions/regressions-dl20-passage-splade-pp-ed.md index bc2c037bb4..d2a914eb0d 100644 --- a/docs/regressions/regressions-dl20-passage-splade-pp-ed.md +++ b/docs/regressions/regressions-dl20-passage-splade-pp-ed.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-ed & ``` @@ -80,21 +80,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl20.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.splade-pp-ed.topics.dl20.splade-pp-ed.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl20.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.rm3.topics.dl20.splade-pp-ed.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl20.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.rocchio.topics.dl20.splade-pp-ed.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl20-passage-splade-pp-sd-onnx.md b/docs/regressions/regressions-dl20-passage-splade-pp-sd-onnx.md index b6dbcef3c0..e19a85ab8a 100644 --- a/docs/regressions/regressions-dl20-passage-splade-pp-sd-onnx.md +++ b/docs/regressions/regressions-dl20-passage-splade-pp-sd-onnx.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-sd & ``` @@ -80,21 +80,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.splade-pp-sd.topics.dl20.txt \ -impact -pretokenized -encoder SpladePlusPlusSelfDistil & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.rm3.topics.dl20.txt \ -impact -pretokenized -rm3 -encoder SpladePlusPlusSelfDistil & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.rocchio.topics.dl20.txt \ -impact -pretokenized -rocchio -encoder SpladePlusPlusSelfDistil & ``` diff --git a/docs/regressions/regressions-dl20-passage-splade-pp-sd.md b/docs/regressions/regressions-dl20-passage-splade-pp-sd.md index 59fd108ffd..4c5957e3a1 100644 --- a/docs/regressions/regressions-dl20-passage-splade-pp-sd.md +++ b/docs/regressions/regressions-dl20-passage-splade-pp-sd.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-sd & ``` @@ -80,21 +80,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl20.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.splade-pp-sd.topics.dl20.splade-pp-sd.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl20.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.rm3.topics.dl20.splade-pp-sd.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl20.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.rocchio.topics.dl20.splade-pp-sd.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl20-passage-unicoil-noexp.md b/docs/regressions/regressions-dl20-passage-unicoil-noexp.md index a7b603c8ad..bf1d3ce85c 100644 --- a/docs/regressions/regressions-dl20-passage-unicoil-noexp.md +++ b/docs/regressions/regressions-dl20-passage-unicoil-noexp.md @@ -58,8 +58,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-unicoil-noexp \ - -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-unicoil-noexp & ``` @@ -83,21 +83,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil-noexp.unicoil.topics.dl20.unicoil-noexp.0shot.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil-noexp.rm3.topics.dl20.unicoil-noexp.0shot.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil-noexp.rocchio.topics.dl20.unicoil-noexp.0shot.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl20-passage-unicoil.md b/docs/regressions/regressions-dl20-passage-unicoil.md index 08b7d805ac..2867bc5123 100644 --- a/docs/regressions/regressions-dl20-passage-unicoil.md +++ b/docs/regressions/regressions-dl20-passage-unicoil.md @@ -58,8 +58,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-unicoil \ - -index indexes/lucene-index.msmarco-passage-unicoil/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-unicoil/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-unicoil & ``` @@ -83,21 +83,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil.unicoil.topics.dl20.unicoil.0shot.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil.rm3.topics.dl20.unicoil.0shot.txt \ -impact -pretokenized -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil/ \ -topics tools/topics-and-qrels/topics.dl20.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil.rocchio.topics.dl20.unicoil.0shot.txt \ -impact -pretokenized -rocchio & ``` diff --git a/docs/regressions/regressions-dl20-passage-wp.md b/docs/regressions/regressions-dl20-passage-wp.md index c4a669d906..5f087675b1 100644 --- a/docs/regressions/regressions-dl20-passage-wp.md +++ b/docs/regressions/regressions-dl20-passage-wp.md @@ -26,8 +26,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage-wp \ - -index indexes/lucene-index.msmarco-passage-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-wp/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-passage-wp & ``` @@ -48,7 +48,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-wp/ \ -topics tools/topics-and-qrels/topics.dl20.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-wp.bm25-default.topics.dl20.wp.txt \ -bm25 -pretokenized & ``` diff --git a/docs/regressions/regressions-dl20-passage.md b/docs/regressions/regressions-dl20-passage.md index de15762936..eac86f1ba6 100644 --- a/docs/regressions/regressions-dl20-passage.md +++ b/docs/regressions/regressions-dl20-passage.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage \ - -index indexes/lucene-index.msmarco-passage/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage/ \ -threads 9 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-passage & ``` @@ -47,84 +47,84 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default.topics.dl20.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+rm3.topics.dl20.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+rocchio.topics.dl20.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+rocchio-neg.topics.dl20.txt \ -bm25 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+ax.topics.dl20.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default+prf.topics.dl20.txt \ -bm25 -bm25prf & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+rm3.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+rocchio.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+rocchio-neg.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -rocchio -rocchio.useNegative -rerankCutoff 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+ax.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.dl20.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned+prf.topics.dl20.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 -bm25prf & ``` diff --git a/docs/regressions/regressions-dl21-doc-d2q-t5.md b/docs/regressions/regressions-dl21-doc-d2q-t5.md index ae6f946e08..7ac433b078 100644 --- a/docs/regressions/regressions-dl21-doc-d2q-t5.md +++ b/docs/regressions/regressions-dl21-doc-d2q-t5.md @@ -29,8 +29,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2DocCollection \ -input /path/to/msmarco-v2-doc-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-doc-d2q-t5 & ``` @@ -52,21 +52,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-d2q-t5.bm25-default.topics.dl21.txt \ -hits 1000 -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-d2q-t5.bm25-default+rm3.topics.dl21.txt \ -hits 1000 -bm25 -rm3 -collection MsMarcoV2DocCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-d2q-t5.bm25-default+rocchio.topics.dl21.txt \ -hits 1000 -bm25 -rocchio -collection MsMarcoV2DocCollection & ``` diff --git a/docs/regressions/regressions-dl21-doc-segmented-d2q-t5.md b/docs/regressions/regressions-dl21-doc-segmented-d2q-t5.md index 4fe37bd328..cc0ae305e7 100644 --- a/docs/regressions/regressions-dl21-doc-segmented-d2q-t5.md +++ b/docs/regressions/regressions-dl21-doc-segmented-d2q-t5.md @@ -29,8 +29,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2DocCollection \ -input /path/to/msmarco-v2-doc-segmented-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-doc-segmented-d2q-t5 & ``` @@ -52,21 +52,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-d2q-t5.bm25-default.topics.dl21.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-d2q-t5.bm25-default+rm3.topics.dl21.txt \ -bm25 -rm3 -collection MsMarcoV2DocCollection -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-d2q-t5.bm25-default+rocchio.topics.dl21.txt \ -bm25 -rocchio -collection MsMarcoV2DocCollection -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl21-doc-segmented-unicoil-0shot-v2.md b/docs/regressions/regressions-dl21-doc-segmented-unicoil-0shot-v2.md index 82f49c14da..ca060c1902 100644 --- a/docs/regressions/regressions-dl21-doc-segmented-unicoil-0shot-v2.md +++ b/docs/regressions/regressions-dl21-doc-segmented-unicoil-0shot-v2.md @@ -69,8 +69,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-doc-segmented-unicoil-0shot-v2 \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-doc-segmented-unicoil-0shot-v2 & ``` @@ -94,21 +94,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-0shot-v2.unicoil-0shot.topics.dl21.unicoil.0shot.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-0shot-v2.unicoil-0shot+rm3.topics.dl21.unicoil.0shot.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-0shot-v2.unicoil-0shot+rocchio.topics.dl21.unicoil.0shot.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl21-doc-segmented-unicoil-0shot.md b/docs/regressions/regressions-dl21-doc-segmented-unicoil-0shot.md index 04caf1033f..dbb0e4d45e 100644 --- a/docs/regressions/regressions-dl21-doc-segmented-unicoil-0shot.md +++ b/docs/regressions/regressions-dl21-doc-segmented-unicoil-0shot.md @@ -68,8 +68,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-doc-segmented-unicoil-0shot \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot/ \ -threads 24 -impact -pretokenized \ >& logs/log.msmarco-v2-doc-segmented-unicoil-0shot & ``` @@ -93,7 +93,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-0shot.unicoil-0shot.topics.dl21.unicoil.0shot.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-dl21-doc-segmented-unicoil-noexp-0shot-v2.md b/docs/regressions/regressions-dl21-doc-segmented-unicoil-noexp-0shot-v2.md index 1386d9238a..d15f7054e8 100644 --- a/docs/regressions/regressions-dl21-doc-segmented-unicoil-noexp-0shot-v2.md +++ b/docs/regressions/regressions-dl21-doc-segmented-unicoil-noexp-0shot-v2.md @@ -69,8 +69,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2 \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2 & ``` @@ -94,21 +94,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.unicoil-noexp-0shot.topics.dl21.unicoil-noexp.0shot.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.unicoil-noexp-0shot+rm3.topics.dl21.unicoil-noexp.0shot.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.unicoil-noexp-0shot+rocchio.topics.dl21.unicoil-noexp.0shot.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl21-doc-segmented-unicoil-noexp-0shot.md b/docs/regressions/regressions-dl21-doc-segmented-unicoil-noexp-0shot.md index ce879b072e..b6b199dd3b 100644 --- a/docs/regressions/regressions-dl21-doc-segmented-unicoil-noexp-0shot.md +++ b/docs/regressions/regressions-dl21-doc-segmented-unicoil-noexp-0shot.md @@ -68,8 +68,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-doc-segmented-unicoil-noexp-0shot \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot/ \ -threads 24 -impact -pretokenized \ >& logs/log.msmarco-v2-doc-segmented-unicoil-noexp-0shot & ``` @@ -93,7 +93,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-noexp-0shot.unicoil-noexp-0shot.topics.dl21.unicoil-noexp.0shot.txt \ -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-dl21-doc-segmented.md b/docs/regressions/regressions-dl21-doc-segmented.md index 14e0ff5e27..229a37a855 100644 --- a/docs/regressions/regressions-dl21-doc-segmented.md +++ b/docs/regressions/regressions-dl21-doc-segmented.md @@ -29,8 +29,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2DocCollection \ -input /path/to/msmarco-v2-doc-segmented \ - -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-doc-segmented & ``` @@ -52,21 +52,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented.bm25-default.topics.dl21.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented.bm25-default+rm3.topics.dl21.txt \ -bm25 -rm3 -collection MsMarcoV2DocCollection -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented.bm25-default+rocchio.topics.dl21.txt \ -bm25 -rocchio -collection MsMarcoV2DocCollection -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-dl21-doc.md b/docs/regressions/regressions-dl21-doc.md index 962bb601b6..7d90c151b7 100644 --- a/docs/regressions/regressions-dl21-doc.md +++ b/docs/regressions/regressions-dl21-doc.md @@ -29,8 +29,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2DocCollection \ -input /path/to/msmarco-v2-doc \ - -index indexes/lucene-index.msmarco-v2-doc/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-doc & ``` @@ -52,21 +52,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc.bm25-default.topics.dl21.txt \ -hits 1000 -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc.bm25-default+rm3.topics.dl21.txt \ -hits 1000 -bm25 -rm3 -collection MsMarcoV2DocCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc.bm25-default+rocchio.topics.dl21.txt \ -hits 1000 -bm25 -rocchio -collection MsMarcoV2DocCollection & ``` diff --git a/docs/regressions/regressions-dl21-passage-augmented-d2q-t5.md b/docs/regressions/regressions-dl21-passage-augmented-d2q-t5.md index e969f18987..8f3af1dbfe 100644 --- a/docs/regressions/regressions-dl21-passage-augmented-d2q-t5.md +++ b/docs/regressions/regressions-dl21-passage-augmented-d2q-t5.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-augmented-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-augmented-d2q-t5 & ``` @@ -47,21 +47,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented-d2q-t5.bm25-default.topics.dl21.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented-d2q-t5.bm25-default+rm3.topics.dl21.txt \ -bm25 -rm3 -collection MsMarcoV2PassageCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented-d2q-t5.bm25-default+rocchio.topics.dl21.txt \ -bm25 -rocchio -collection MsMarcoV2PassageCollection & ``` diff --git a/docs/regressions/regressions-dl21-passage-augmented.md b/docs/regressions/regressions-dl21-passage-augmented.md index d887c5a481..d5356e9a75 100644 --- a/docs/regressions/regressions-dl21-passage-augmented.md +++ b/docs/regressions/regressions-dl21-passage-augmented.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-augmented \ - -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-augmented & ``` @@ -47,21 +47,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented.bm25-default.topics.dl21.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented.bm25-default+rm3.topics.dl21.txt \ -bm25 -rm3 -collection MsMarcoV2PassageCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented.bm25-default+rocchio.topics.dl21.txt \ -bm25 -rocchio -collection MsMarcoV2PassageCollection & ``` diff --git a/docs/regressions/regressions-dl21-passage-d2q-t5.md b/docs/regressions/regressions-dl21-passage-d2q-t5.md index 05c586105c..b4fd45df1a 100644 --- a/docs/regressions/regressions-dl21-passage-d2q-t5.md +++ b/docs/regressions/regressions-dl21-passage-d2q-t5.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-d2q-t5 & ``` @@ -47,21 +47,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-d2q-t5.bm25-default.topics.dl21.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-d2q-t5.bm25-default+rm3.topics.dl21.txt \ -bm25 -rm3 -collection MsMarcoV2PassageCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-d2q-t5.bm25-default+rocchio.topics.dl21.txt \ -bm25 -rocchio -collection MsMarcoV2PassageCollection & ``` diff --git a/docs/regressions/regressions-dl21-passage-splade-pp-ed.md b/docs/regressions/regressions-dl21-passage-splade-pp-ed.md index b0e1c97460..14c44d82fb 100644 --- a/docs/regressions/regressions-dl21-passage-splade-pp-ed.md +++ b/docs/regressions/regressions-dl21-passage-splade-pp-ed.md @@ -54,8 +54,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-splade-pp-ed & ``` @@ -79,21 +79,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl21.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-ed.splade-pp-ed.topics.dl21.splade-pp-ed.txt \ -parallelism 16 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl21.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-ed.splade-pp-ed+rm3.topics.dl21.splade-pp-ed.txt \ -parallelism 16 -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl21.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-ed.splade-pp-ed+rocchio.topics.dl21.splade-pp-ed.txt \ -parallelism 16 -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl21-passage-splade-pp-sd.md b/docs/regressions/regressions-dl21-passage-splade-pp-sd.md index f2ade9c756..7ae67a7e86 100644 --- a/docs/regressions/regressions-dl21-passage-splade-pp-sd.md +++ b/docs/regressions/regressions-dl21-passage-splade-pp-sd.md @@ -54,8 +54,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-splade-pp-sd & ``` @@ -79,21 +79,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl21.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-sd.splade-pp-sd.topics.dl21.splade-pp-sd.txt \ -parallelism 16 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl21.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-sd.splade-pp-sd+rm3.topics.dl21.splade-pp-sd.txt \ -parallelism 16 -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl21.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-sd.splade-pp-sd+rocchio.topics.dl21.splade-pp-sd.txt \ -parallelism 16 -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl21-passage-unicoil-0shot.md b/docs/regressions/regressions-dl21-passage-unicoil-0shot.md index 82370c5e97..26d63c683c 100644 --- a/docs/regressions/regressions-dl21-passage-unicoil-0shot.md +++ b/docs/regressions/regressions-dl21-passage-unicoil-0shot.md @@ -63,8 +63,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-unicoil-0shot \ - -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-unicoil-0shot & ``` @@ -88,21 +88,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-0shot.unicoil-0shot.topics.dl21.unicoil.0shot.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-0shot.unicoil-0shot+rm3.topics.dl21.unicoil.0shot.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-0shot.unicoil-0shot+rocchio.topics.dl21.unicoil.0shot.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl21-passage-unicoil-noexp-0shot.md b/docs/regressions/regressions-dl21-passage-unicoil-noexp-0shot.md index 22d5d38beb..8209d6ca7e 100644 --- a/docs/regressions/regressions-dl21-passage-unicoil-noexp-0shot.md +++ b/docs/regressions/regressions-dl21-passage-unicoil-noexp-0shot.md @@ -63,8 +63,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-unicoil-noexp-0shot \ - -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-unicoil-noexp-0shot & ``` @@ -88,21 +88,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-noexp-0shot.unicoil-noexp-0shot.topics.dl21.unicoil-noexp.0shot.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-noexp-0shot.unicoil-noexp-0shot+rm3.topics.dl21.unicoil-noexp.0shot.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.dl21.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-noexp-0shot.unicoil-noexp-0shot+rocchio.topics.dl21.unicoil-noexp.0shot.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl21-passage.md b/docs/regressions/regressions-dl21-passage.md index 7c06872872..c7def52d69 100644 --- a/docs/regressions/regressions-dl21-passage.md +++ b/docs/regressions/regressions-dl21-passage.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage \ - -index indexes/lucene-index.msmarco-v2-passage/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage & ``` @@ -47,21 +47,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage.bm25-default.topics.dl21.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage.bm25-default+rm3.topics.dl21.txt \ -bm25 -rm3 -collection MsMarcoV2PassageCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage/ \ -topics tools/topics-and-qrels/topics.dl21.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage.bm25-default+rocchio.topics.dl21.txt \ -bm25 -rocchio -collection MsMarcoV2PassageCollection & ``` diff --git a/docs/regressions/regressions-dl22-passage-augmented-d2q-t5.md b/docs/regressions/regressions-dl22-passage-augmented-d2q-t5.md index 8f48735b4c..7a2770f82f 100644 --- a/docs/regressions/regressions-dl22-passage-augmented-d2q-t5.md +++ b/docs/regressions/regressions-dl22-passage-augmented-d2q-t5.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-augmented-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-augmented-d2q-t5 & ``` @@ -46,21 +46,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented-d2q-t5.bm25-default.topics.dl22.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented-d2q-t5.bm25-default+rm3.topics.dl22.txt \ -bm25 -rm3 -collection MsMarcoV2PassageCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented-d2q-t5.bm25-default+rocchio.topics.dl22.txt \ -bm25 -rocchio -collection MsMarcoV2PassageCollection & ``` diff --git a/docs/regressions/regressions-dl22-passage-augmented.md b/docs/regressions/regressions-dl22-passage-augmented.md index 2ee3f32c12..7a22a22a98 100644 --- a/docs/regressions/regressions-dl22-passage-augmented.md +++ b/docs/regressions/regressions-dl22-passage-augmented.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-augmented \ - -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-augmented & ``` @@ -46,21 +46,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented.bm25-default.topics.dl22.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented.bm25-default+rm3.topics.dl22.txt \ -bm25 -rm3 -collection MsMarcoV2PassageCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented.bm25-default+rocchio.topics.dl22.txt \ -bm25 -rocchio -collection MsMarcoV2PassageCollection & ``` diff --git a/docs/regressions/regressions-dl22-passage-d2q-t5.md b/docs/regressions/regressions-dl22-passage-d2q-t5.md index 6531b3e380..b5215d08fe 100644 --- a/docs/regressions/regressions-dl22-passage-d2q-t5.md +++ b/docs/regressions/regressions-dl22-passage-d2q-t5.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-d2q-t5 & ``` @@ -46,21 +46,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-d2q-t5.bm25-default.topics.dl22.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-d2q-t5.bm25-default+rm3.topics.dl22.txt \ -bm25 -rm3 -collection MsMarcoV2PassageCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-d2q-t5.bm25-default+rocchio.topics.dl22.txt \ -bm25 -rocchio -collection MsMarcoV2PassageCollection & ``` diff --git a/docs/regressions/regressions-dl22-passage-splade-pp-ed.md b/docs/regressions/regressions-dl22-passage-splade-pp-ed.md index a4bbfada21..1e027a64ba 100644 --- a/docs/regressions/regressions-dl22-passage-splade-pp-ed.md +++ b/docs/regressions/regressions-dl22-passage-splade-pp-ed.md @@ -54,8 +54,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-splade-pp-ed & ``` @@ -78,21 +78,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl22.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-ed.splade-pp-ed.topics.dl22.splade-pp-ed.txt \ -parallelism 16 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl22.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-ed.splade-pp-ed+rm3.topics.dl22.splade-pp-ed.txt \ -parallelism 16 -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.dl22.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-ed.splade-pp-ed+rocchio.topics.dl22.splade-pp-ed.txt \ -parallelism 16 -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl22-passage-splade-pp-sd.md b/docs/regressions/regressions-dl22-passage-splade-pp-sd.md index d410568d2e..ccae618380 100644 --- a/docs/regressions/regressions-dl22-passage-splade-pp-sd.md +++ b/docs/regressions/regressions-dl22-passage-splade-pp-sd.md @@ -54,8 +54,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-splade-pp-sd & ``` @@ -78,21 +78,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl22.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-sd.splade-pp-sd.topics.dl22.splade-pp-sd.txt \ -parallelism 16 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl22.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-sd.splade-pp-sd+rm3.topics.dl22.splade-pp-sd.txt \ -parallelism 16 -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.dl22.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-sd.splade-pp-sd+rocchio.topics.dl22.splade-pp-sd.txt \ -parallelism 16 -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl22-passage-unicoil-0shot.md b/docs/regressions/regressions-dl22-passage-unicoil-0shot.md index 07aa285c5b..5f1b8ae903 100644 --- a/docs/regressions/regressions-dl22-passage-unicoil-0shot.md +++ b/docs/regressions/regressions-dl22-passage-unicoil-0shot.md @@ -63,8 +63,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-unicoil-0shot \ - -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-unicoil-0shot & ``` @@ -87,21 +87,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.dl22.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-0shot.unicoil-0shot.topics.dl22.unicoil.0shot.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.dl22.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-0shot.unicoil-0shot+rm3.topics.dl22.unicoil.0shot.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.dl22.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-0shot.unicoil-0shot+rocchio.topics.dl22.unicoil.0shot.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl22-passage-unicoil-noexp-0shot.md b/docs/regressions/regressions-dl22-passage-unicoil-noexp-0shot.md index 310a135c6f..b9e427668e 100644 --- a/docs/regressions/regressions-dl22-passage-unicoil-noexp-0shot.md +++ b/docs/regressions/regressions-dl22-passage-unicoil-noexp-0shot.md @@ -63,8 +63,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-unicoil-noexp-0shot \ - -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-unicoil-noexp-0shot & ``` @@ -87,21 +87,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.dl22.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-noexp-0shot.unicoil-noexp-0shot.topics.dl22.unicoil-noexp.0shot.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.dl22.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-noexp-0shot.unicoil-noexp-0shot+rm3.topics.dl22.unicoil-noexp.0shot.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.dl22.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-noexp-0shot.unicoil-noexp-0shot+rocchio.topics.dl22.unicoil-noexp.0shot.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-dl22-passage.md b/docs/regressions/regressions-dl22-passage.md index 426bafdbe5..f1171d3c67 100644 --- a/docs/regressions/regressions-dl22-passage.md +++ b/docs/regressions/regressions-dl22-passage.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage \ - -index indexes/lucene-index.msmarco-v2-passage/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage & ``` @@ -46,21 +46,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage.bm25-default.topics.dl22.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage.bm25-default+rm3.topics.dl22.txt \ -bm25 -rm3 -collection MsMarcoV2PassageCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage/ \ -topics tools/topics-and-qrels/topics.dl22.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage.bm25-default+rocchio.topics.dl22.txt \ -bm25 -rocchio -collection MsMarcoV2PassageCollection & ``` diff --git a/docs/regressions/regressions-fever.md b/docs/regressions/regressions-fever.md index 8252ae83bc..2f4391e706 100644 --- a/docs/regressions/regressions-fever.md +++ b/docs/regressions/regressions-fever.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection FeverParagraphCollection \ -input /path/to/fever \ - -index indexes/lucene-index.fever-paragraph/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.fever-paragraph/ \ -threads 1 -storePositions -storeDocvectors -storeRaw \ >& logs/log.fever & ``` @@ -41,14 +41,14 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.fever-paragraph/ \ -topics tools/topics-and-qrels/topics.fever.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.fever.bm25-default.topics.fever.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.fever-paragraph/ \ -topics tools/topics-and-qrels/topics.fever.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.fever.bm25-tuned.topics.fever.dev.txt \ -bm25 -bm25.k1 0.9 -bm25.b 0.1 & ``` diff --git a/docs/regressions/regressions-fire12-bn.md b/docs/regressions/regressions-fire12-bn.md index 4b3732f4ba..b9d0faeddd 100644 --- a/docs/regressions/regressions-fire12-bn.md +++ b/docs/regressions/regressions-fire12-bn.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection CleanTrecCollection \ -input /path/to/fire12-bn \ - -index indexes/lucene-index.fire12-bn/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.fire12-bn/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language bn \ >& logs/log.fire12-bn & ``` @@ -45,7 +45,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.fire12-bn/ \ -topics tools/topics-and-qrels/topics.fire12bn.176-225.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.fire12-bn.bm25.topics.fire12bn.176-225.txt \ -bm25 -language bn & ``` diff --git a/docs/regressions/regressions-fire12-en.md b/docs/regressions/regressions-fire12-en.md index a24224aa0c..4edca45887 100644 --- a/docs/regressions/regressions-fire12-en.md +++ b/docs/regressions/regressions-fire12-en.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection CleanTrecCollection \ -input /path/to/fire12-en \ - -index indexes/lucene-index.fire12-en/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.fire12-en/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language en \ >& logs/log.fire12-en & ``` @@ -45,7 +45,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.fire12-en/ \ -topics tools/topics-and-qrels/topics.fire12en.176-225.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.fire12-en.bm25.topics.fire12en.176-225.txt \ -bm25 -language en & ``` diff --git a/docs/regressions/regressions-fire12-hi.md b/docs/regressions/regressions-fire12-hi.md index c9fb43f662..b6579352e7 100644 --- a/docs/regressions/regressions-fire12-hi.md +++ b/docs/regressions/regressions-fire12-hi.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection CleanTrecCollection \ -input /path/to/fire12-hi \ - -index indexes/lucene-index.fire12-hi/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.fire12-hi/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language hi \ >& logs/log.fire12-hi & ``` @@ -45,7 +45,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.fire12-hi/ \ -topics tools/topics-and-qrels/topics.fire12hi.176-225.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.fire12-hi.bm25.topics.fire12hi.176-225.txt \ -bm25 -language hi & ``` diff --git a/docs/regressions/regressions-gov2.md b/docs/regressions/regressions-gov2.md index 3b83c63d10..3d88e24227 100644 --- a/docs/regressions/regressions-gov2.md +++ b/docs/regressions/regressions-gov2.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection TrecwebCollection \ -input /path/to/gov2 \ - -index indexes/lucene-index.gov2/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.gov2/ \ -threads 44 -storePositions -storeDocvectors -storeRaw \ >& logs/log.gov2 & ``` @@ -48,114 +48,114 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte04.701-750.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25.topics.terabyte04.701-750.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte05.751-800.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25.topics.terabyte05.751-800.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte06.801-850.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25.topics.terabyte06.801-850.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte04.701-750.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25+rm3.topics.terabyte04.701-750.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte05.751-800.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25+rm3.topics.terabyte05.751-800.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte06.801-850.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25+rm3.topics.terabyte06.801-850.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte04.701-750.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25+ax.topics.terabyte04.701-750.txt \ -bm25 -axiom -axiom.beta 0.1 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte05.751-800.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25+ax.topics.terabyte05.751-800.txt \ -bm25 -axiom -axiom.beta 0.1 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte06.801-850.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.bm25+ax.topics.terabyte06.801-850.txt \ -bm25 -axiom -axiom.beta 0.1 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte04.701-750.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql.topics.terabyte04.701-750.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte05.751-800.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql.topics.terabyte05.751-800.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte06.801-850.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql.topics.terabyte06.801-850.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte04.701-750.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql+rm3.topics.terabyte04.701-750.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte05.751-800.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql+rm3.topics.terabyte05.751-800.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte06.801-850.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql+rm3.topics.terabyte06.801-850.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte04.701-750.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql+ax.topics.terabyte04.701-750.txt \ -qld -axiom -axiom.beta 0.1 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte05.751-800.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql+ax.topics.terabyte05.751-800.txt \ -qld -axiom -axiom.beta 0.1 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.gov2/ \ -topics tools/topics-and-qrels/topics.terabyte06.801-850.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.gov2.ql+ax.topics.terabyte06.801-850.txt \ -qld -axiom -axiom.beta 0.1 -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-hc4-neuclir22-fa-en.md b/docs/regressions/regressions-hc4-neuclir22-fa-en.md index b9a988ebd0..a00418ae07 100644 --- a/docs/regressions/regressions-hc4-neuclir22-fa-en.md +++ b/docs/regressions/regressions-hc4-neuclir22-fa-en.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-fa-en \ - -index indexes/lucene-index.neuclir22-fa-en \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-fa-en \ -threads 8 -storePositions -storeDocvectors -storeRaw \ >& logs/log.neuclir22-fa-en & ``` @@ -51,57 +51,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default.topics.hc4-v1.0-fa.en.test.title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default.topics.hc4-v1.0-fa.en.test.desc.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default.topics.hc4-v1.0-fa.en.test.desc.title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rm3.topics.hc4-v1.0-fa.en.test.title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rm3.topics.hc4-v1.0-fa.en.test.desc.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rm3.topics.hc4-v1.0-fa.en.test.desc.title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rocchio.topics.hc4-v1.0-fa.en.test.title.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rocchio.topics.hc4-v1.0-fa.en.test.desc.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rocchio.topics.hc4-v1.0-fa.en.test.desc.title.txt \ -bm25 -rocchio & ``` diff --git a/docs/regressions/regressions-hc4-neuclir22-fa.md b/docs/regressions/regressions-hc4-neuclir22-fa.md index 749e7099c4..c0d4519408 100644 --- a/docs/regressions/regressions-hc4-neuclir22-fa.md +++ b/docs/regressions/regressions-hc4-neuclir22-fa.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-fa \ - -index indexes/lucene-index.neuclir22-fa \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-fa \ -threads 8 -storePositions -storeDocvectors -storeRaw -language fa \ >& logs/log.neuclir22-fa & ``` @@ -51,57 +51,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.hc4-v1.0-fa.test.title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.hc4-v1.0-fa.test.desc.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.hc4-v1.0-fa.test.desc.title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.hc4-v1.0-fa.test.title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.hc4-v1.0-fa.test.desc.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.hc4-v1.0-fa.test.desc.title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.test.title.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.test.desc.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.test.desc.title.txt \ -bm25 -rocchio -language fa & ``` diff --git a/docs/regressions/regressions-hc4-neuclir22-ru-en.md b/docs/regressions/regressions-hc4-neuclir22-ru-en.md index b0b28311e5..8d819bcedd 100644 --- a/docs/regressions/regressions-hc4-neuclir22-ru-en.md +++ b/docs/regressions/regressions-hc4-neuclir22-ru-en.md @@ -35,8 +35,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-ru-en \ - -index indexes/lucene-index.neuclir22-ru-en \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-ru-en \ -threads 8 -storePositions -storeDocvectors -storeRaw \ >& logs/log.neuclir22-ru-en & ``` @@ -52,57 +52,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default.topics.hc4-v1.0-ru.en.test.title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default.topics.hc4-v1.0-ru.en.test.desc.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default.topics.hc4-v1.0-ru.en.test.desc.title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rm3.topics.hc4-v1.0-ru.en.test.title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rm3.topics.hc4-v1.0-ru.en.test.desc.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rm3.topics.hc4-v1.0-ru.en.test.desc.title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rocchio.topics.hc4-v1.0-ru.en.test.title.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rocchio.topics.hc4-v1.0-ru.en.test.desc.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rocchio.topics.hc4-v1.0-ru.en.test.desc.title.txt \ -bm25 -rocchio & ``` diff --git a/docs/regressions/regressions-hc4-neuclir22-ru.md b/docs/regressions/regressions-hc4-neuclir22-ru.md index ee3a5eacb2..5ea98c5188 100644 --- a/docs/regressions/regressions-hc4-neuclir22-ru.md +++ b/docs/regressions/regressions-hc4-neuclir22-ru.md @@ -35,8 +35,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-ru \ - -index indexes/lucene-index.neuclir22-ru \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-ru \ -threads 8 -storePositions -storeDocvectors -storeRaw -language ru \ >& logs/log.neuclir22-ru & ``` @@ -52,57 +52,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.hc4-v1.0-ru.test.title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.hc4-v1.0-ru.test.desc.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.hc4-v1.0-ru.test.desc.title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.hc4-v1.0-ru.test.title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.hc4-v1.0-ru.test.desc.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.hc4-v1.0-ru.test.desc.title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.test.title.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.test.desc.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.test.desc.title.txt \ -bm25 -rocchio -language ru & ``` diff --git a/docs/regressions/regressions-hc4-neuclir22-zh-en.md b/docs/regressions/regressions-hc4-neuclir22-zh-en.md index 2bbbc4ffd9..d0580bd8a2 100644 --- a/docs/regressions/regressions-hc4-neuclir22-zh-en.md +++ b/docs/regressions/regressions-hc4-neuclir22-zh-en.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-zh-en \ - -index indexes/lucene-index.neuclir22-zh-en \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-zh-en \ -threads 8 -storePositions -storeDocvectors -storeRaw \ >& logs/log.neuclir22-zh-en & ``` @@ -51,57 +51,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default.topics.hc4-v1.0-zh.en.test.title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default.topics.hc4-v1.0-zh.en.test.desc.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default.topics.hc4-v1.0-zh.en.test.desc.title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rm3.topics.hc4-v1.0-zh.en.test.title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rm3.topics.hc4-v1.0-zh.en.test.desc.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rm3.topics.hc4-v1.0-zh.en.test.desc.title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rocchio.topics.hc4-v1.0-zh.en.test.title.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rocchio.topics.hc4-v1.0-zh.en.test.desc.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.en.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rocchio.topics.hc4-v1.0-zh.en.test.desc.title.txt \ -bm25 -rocchio & ``` diff --git a/docs/regressions/regressions-hc4-neuclir22-zh.md b/docs/regressions/regressions-hc4-neuclir22-zh.md index 40c7edcd34..1867566e98 100644 --- a/docs/regressions/regressions-hc4-neuclir22-zh.md +++ b/docs/regressions/regressions-hc4-neuclir22-zh.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-zh \ - -index indexes/lucene-index.neuclir22-zh \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-zh \ -threads 8 -storePositions -storeDocvectors -storeRaw -language zh \ >& logs/log.neuclir22-zh & ``` @@ -51,57 +51,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.hc4-v1.0-zh.test.title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.hc4-v1.0-zh.test.desc.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.hc4-v1.0-zh.test.desc.title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.hc4-v1.0-zh.test.title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.hc4-v1.0-zh.test.desc.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.hc4-v1.0-zh.test.desc.title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.test.title.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.test.desc.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.test.desc.title.txt \ -bm25 -rocchio -language zh & ``` diff --git a/docs/regressions/regressions-hc4-v1.0-fa.md b/docs/regressions/regressions-hc4-v1.0-fa.md index 2b7bfcf52a..73ab546d6d 100644 --- a/docs/regressions/regressions-hc4-v1.0-fa.md +++ b/docs/regressions/regressions-hc4-v1.0-fa.md @@ -33,8 +33,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/hc4-v1.0-fa \ - -index indexes/lucene-index.hc4-v1.0-fa \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.hc4-v1.0-fa \ -threads 8 -storePositions -storeDocvectors -storeRaw -language fa \ >& logs/log.hc4-v1.0-fa & ``` @@ -50,111 +50,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default.topics.hc4-v1.0-fa.dev.title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default.topics.hc4-v1.0-fa.dev.desc.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default.topics.hc4-v1.0-fa.dev.desc.title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default.topics.hc4-v1.0-fa.test.title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default.topics.hc4-v1.0-fa.test.desc.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default.topics.hc4-v1.0-fa.test.desc.title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rm3.topics.hc4-v1.0-fa.dev.title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rm3.topics.hc4-v1.0-fa.dev.desc.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rm3.topics.hc4-v1.0-fa.dev.desc.title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rm3.topics.hc4-v1.0-fa.test.title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rm3.topics.hc4-v1.0-fa.test.desc.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rm3.topics.hc4-v1.0-fa.test.desc.title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.dev.title.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.dev.desc.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.dev.desc.title.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.test.title.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.test.desc.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-fa \ -topics tools/topics-and-qrels/topics.hc4-v1.0-fa.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-fa.bm25-default+rocchio.topics.hc4-v1.0-fa.test.desc.title.txt \ -bm25 -rocchio -language fa & ``` diff --git a/docs/regressions/regressions-hc4-v1.0-ru.md b/docs/regressions/regressions-hc4-v1.0-ru.md index a0f7dd857e..b5d6d33372 100644 --- a/docs/regressions/regressions-hc4-v1.0-ru.md +++ b/docs/regressions/regressions-hc4-v1.0-ru.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/hc4-v1.0-ru \ - -index indexes/lucene-index.hc4-v1.0-ru \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.hc4-v1.0-ru \ -threads 8 -storePositions -storeDocvectors -storeRaw -language ru \ >& logs/log.hc4-v1.0-ru & ``` @@ -51,111 +51,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default.topics.hc4-v1.0-ru.dev.title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default.topics.hc4-v1.0-ru.dev.desc.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default.topics.hc4-v1.0-ru.dev.desc.title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default.topics.hc4-v1.0-ru.test.title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default.topics.hc4-v1.0-ru.test.desc.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default.topics.hc4-v1.0-ru.test.desc.title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rm3.topics.hc4-v1.0-ru.dev.title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rm3.topics.hc4-v1.0-ru.dev.desc.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rm3.topics.hc4-v1.0-ru.dev.desc.title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rm3.topics.hc4-v1.0-ru.test.title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rm3.topics.hc4-v1.0-ru.test.desc.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rm3.topics.hc4-v1.0-ru.test.desc.title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.dev.title.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.dev.desc.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.dev.desc.title.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.test.title.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.test.desc.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-ru \ -topics tools/topics-and-qrels/topics.hc4-v1.0-ru.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-ru.bm25-default+rocchio.topics.hc4-v1.0-ru.test.desc.title.txt \ -bm25 -rocchio -language ru & ``` diff --git a/docs/regressions/regressions-hc4-v1.0-zh.md b/docs/regressions/regressions-hc4-v1.0-zh.md index 2af1f33b4b..3d6cd5470b 100644 --- a/docs/regressions/regressions-hc4-v1.0-zh.md +++ b/docs/regressions/regressions-hc4-v1.0-zh.md @@ -33,8 +33,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/hc4-v1.0-zh \ - -index indexes/lucene-index.hc4-v1.0-zh \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.hc4-v1.0-zh \ -threads 8 -storePositions -storeDocvectors -storeRaw -language zh \ >& logs/log.hc4-v1.0-zh & ``` @@ -50,111 +50,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default.topics.hc4-v1.0-zh.dev.title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default.topics.hc4-v1.0-zh.dev.desc.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default.topics.hc4-v1.0-zh.dev.desc.title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default.topics.hc4-v1.0-zh.test.title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default.topics.hc4-v1.0-zh.test.desc.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default.topics.hc4-v1.0-zh.test.desc.title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rm3.topics.hc4-v1.0-zh.dev.title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rm3.topics.hc4-v1.0-zh.dev.desc.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rm3.topics.hc4-v1.0-zh.dev.desc.title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rm3.topics.hc4-v1.0-zh.test.title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rm3.topics.hc4-v1.0-zh.test.desc.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rm3.topics.hc4-v1.0-zh.test.desc.title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.dev.title.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.dev.desc.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.dev.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.dev.desc.title.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.test.title.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.test.desc.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.hc4-v1.0-zh \ -topics tools/topics-and-qrels/topics.hc4-v1.0-zh.test.desc.title.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.hc4-v1.0-zh.bm25-default+rocchio.topics.hc4-v1.0-zh.test.desc.title.txt \ -bm25 -rocchio -language zh & ``` diff --git a/docs/regressions/regressions-mb11.md b/docs/regressions/regressions-mb11.md index 737062fe1d..e748171dad 100644 --- a/docs/regressions/regressions-mb11.md +++ b/docs/regressions/regressions-mb11.md @@ -23,8 +23,8 @@ Indexing the Tweets2011 collection: target/appassembler/bin/IndexCollection \ -collection TweetCollection \ -input /path/to/mb11 \ - -index indexes/lucene-index.mb11/ \ -generator TweetGenerator \ + -index indexes/lucene-index.mb11/ \ -threads 44 -storePositions -storeDocvectors -storeRaw -uniqueDocid -tweet.keepUrls -tweet.stemming \ >& logs/log.mb11 & ``` @@ -54,78 +54,78 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2011.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.bm25.topics.microblog2011.txt \ -searchtweets -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2012.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.bm25.topics.microblog2012.txt \ -searchtweets -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2011.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.bm25+rm3.topics.microblog2011.txt \ -searchtweets -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2012.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.bm25+rm3.topics.microblog2012.txt \ -searchtweets -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2011.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.bm25+ax.topics.microblog2011.txt \ -searchtweets -bm25 -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2012.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.bm25+ax.topics.microblog2012.txt \ -searchtweets -bm25 -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2011.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.ql.topics.microblog2011.txt \ -searchtweets -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2012.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.ql.topics.microblog2012.txt \ -searchtweets -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2011.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.ql+rm3.topics.microblog2011.txt \ -searchtweets -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2012.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.ql+rm3.topics.microblog2012.txt \ -searchtweets -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2011.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.ql+ax.topics.microblog2011.txt \ -searchtweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb11/ \ -topics tools/topics-and-qrels/topics.microblog2012.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb11.ql+ax.topics.microblog2012.txt \ -searchtweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-mb13.md b/docs/regressions/regressions-mb13.md index 9aecbdce7e..5823a1af5a 100644 --- a/docs/regressions/regressions-mb13.md +++ b/docs/regressions/regressions-mb13.md @@ -23,8 +23,8 @@ Indexing the Tweets2013 collection: target/appassembler/bin/IndexCollection \ -collection TweetCollection \ -input /path/to/mb13 \ - -index indexes/lucene-index.mb13/ \ -generator TweetGenerator \ + -index indexes/lucene-index.mb13/ \ -threads 44 -storePositions -storeDocvectors -storeRaw -uniqueDocid -optimize -tweet.keepUrls -tweet.stemming \ >& logs/log.mb13 & ``` @@ -54,78 +54,78 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2013.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.bm25.topics.microblog2013.txt \ -searchtweets -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2014.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.bm25.topics.microblog2014.txt \ -searchtweets -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2013.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.bm25+rm3.topics.microblog2013.txt \ -searchtweets -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2014.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.bm25+rm3.topics.microblog2014.txt \ -searchtweets -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2013.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.bm25+ax.topics.microblog2013.txt \ -searchtweets -bm25 -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2014.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.bm25+ax.topics.microblog2014.txt \ -searchtweets -bm25 -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2013.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.ql.topics.microblog2013.txt \ -searchtweets -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2014.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.ql.topics.microblog2014.txt \ -searchtweets -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2013.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.ql+rm3.topics.microblog2013.txt \ -searchtweets -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2014.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.ql+rm3.topics.microblog2014.txt \ -searchtweets -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2013.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.ql+ax.topics.microblog2013.txt \ -searchtweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mb13/ \ -topics tools/topics-and-qrels/topics.microblog2014.txt \ - -topicreader Microblog \ + -topicReader Microblog \ -output runs/run.mb13.ql+ax.topics.microblog2014.txt \ -searchtweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-ar-aca.md b/docs/regressions/regressions-miracl-v1.0-ar-aca.md index b2a105600c..668bc2ee35 100644 --- a/docs/regressions/regressions-miracl-v1.0-ar-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-ar-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-ar \ - -index indexes/lucene-index.miracl-v1.0-ar-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-ar-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ar -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-ar & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-ar-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-ar-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-ar.bm25.topics.miracl-v1.0-ar-dev.txt \ -bm25 -hits 100 -language ar -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-ar.md b/docs/regressions/regressions-miracl-v1.0-ar.md index e8d8687310..e41a63c37b 100644 --- a/docs/regressions/regressions-miracl-v1.0-ar.md +++ b/docs/regressions/regressions-miracl-v1.0-ar.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-ar \ - -index indexes/lucene-index.miracl-v1.0-ar/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-ar/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ar \ >& logs/log.miracl-v1.0-ar & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-ar/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-ar-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-ar.bm25.topics.miracl-v1.0-ar-dev.txt \ -bm25 -hits 100 -language ar & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-bn-aca.md b/docs/regressions/regressions-miracl-v1.0-bn-aca.md index 19631e59bd..95b3962941 100644 --- a/docs/regressions/regressions-miracl-v1.0-bn-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-bn-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-bn \ - -index indexes/lucene-index.miracl-v1.0-bn-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-bn-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language bn -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-bn & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-bn-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-bn-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-bn.bm25.topics.miracl-v1.0-bn-dev.txt \ -bm25 -hits 100 -language bn -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-bn.md b/docs/regressions/regressions-miracl-v1.0-bn.md index a7f70455fc..66a8ec0bbc 100644 --- a/docs/regressions/regressions-miracl-v1.0-bn.md +++ b/docs/regressions/regressions-miracl-v1.0-bn.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-bn \ - -index indexes/lucene-index.miracl-v1.0-bn/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-bn/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language bn \ >& logs/log.miracl-v1.0-bn & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-bn/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-bn-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-bn.bm25.topics.miracl-v1.0-bn-dev.txt \ -bm25 -hits 100 -language bn & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-en-aca.md b/docs/regressions/regressions-miracl-v1.0-en-aca.md index 986d0e5836..15e75e18e3 100644 --- a/docs/regressions/regressions-miracl-v1.0-en-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-en-aca.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-en \ - -index indexes/lucene-index.miracl-v1.0-en-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-en-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language en -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-en & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-en-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-en-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-en.bm25.topics.miracl-v1.0-en-dev.txt \ -bm25 -hits 100 -language en -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-en.md b/docs/regressions/regressions-miracl-v1.0-en.md index f08cde17e0..6989e277ab 100644 --- a/docs/regressions/regressions-miracl-v1.0-en.md +++ b/docs/regressions/regressions-miracl-v1.0-en.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-en \ - -index indexes/lucene-index.miracl-v1.0-en/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-en/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language en \ >& logs/log.miracl-v1.0-en & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-en/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-en-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-en.bm25.topics.miracl-v1.0-en-dev.txt \ -bm25 -hits 100 -language en & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-es-aca.md b/docs/regressions/regressions-miracl-v1.0-es-aca.md index 4cf2a8f6dd..5e64cf07e7 100644 --- a/docs/regressions/regressions-miracl-v1.0-es-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-es-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-es \ - -index indexes/lucene-index.miracl-v1.0-es-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-es-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language es -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-es & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-es-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-es-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-es.bm25.topics.miracl-v1.0-es-dev.txt \ -bm25 -hits 100 -language es -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-es.md b/docs/regressions/regressions-miracl-v1.0-es.md index cffc92ca8b..b5073475b7 100644 --- a/docs/regressions/regressions-miracl-v1.0-es.md +++ b/docs/regressions/regressions-miracl-v1.0-es.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-es \ - -index indexes/lucene-index.miracl-v1.0-es/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-es/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language es \ >& logs/log.miracl-v1.0-es & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-es/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-es-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-es.bm25.topics.miracl-v1.0-es-dev.txt \ -bm25 -hits 100 -language es & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-fa-aca.md b/docs/regressions/regressions-miracl-v1.0-fa-aca.md index d3fd4537a1..f5b41e0698 100644 --- a/docs/regressions/regressions-miracl-v1.0-fa-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-fa-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-fa \ - -index indexes/lucene-index.miracl-v1.0-fa-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-fa-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language fa -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-fa & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-fa-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-fa-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-fa.bm25.topics.miracl-v1.0-fa-dev.txt \ -bm25 -hits 100 -language fa -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-fa.md b/docs/regressions/regressions-miracl-v1.0-fa.md index 674a4bcae7..f207ae0771 100644 --- a/docs/regressions/regressions-miracl-v1.0-fa.md +++ b/docs/regressions/regressions-miracl-v1.0-fa.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-fa \ - -index indexes/lucene-index.miracl-v1.0-fa/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-fa/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language fa \ >& logs/log.miracl-v1.0-fa & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-fa/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-fa-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-fa.bm25.topics.miracl-v1.0-fa-dev.txt \ -bm25 -hits 100 -language fa & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-fi-aca.md b/docs/regressions/regressions-miracl-v1.0-fi-aca.md index 937f2f0650..9bece4b32f 100644 --- a/docs/regressions/regressions-miracl-v1.0-fi-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-fi-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-fi \ - -index indexes/lucene-index.miracl-v1.0-fi-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-fi-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language fi -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-fi & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-fi-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-fi-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-fi.bm25.topics.miracl-v1.0-fi-dev.txt \ -bm25 -hits 100 -language fi -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-fi.md b/docs/regressions/regressions-miracl-v1.0-fi.md index 3256bfce15..291bed5674 100644 --- a/docs/regressions/regressions-miracl-v1.0-fi.md +++ b/docs/regressions/regressions-miracl-v1.0-fi.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-fi \ - -index indexes/lucene-index.miracl-v1.0-fi/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-fi/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language fi \ >& logs/log.miracl-v1.0-fi & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-fi/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-fi-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-fi.bm25.topics.miracl-v1.0-fi-dev.txt \ -bm25 -hits 100 -language fi & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-fr-aca.md b/docs/regressions/regressions-miracl-v1.0-fr-aca.md index 041fc7afd2..d57ad815f9 100644 --- a/docs/regressions/regressions-miracl-v1.0-fr-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-fr-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-fr \ - -index indexes/lucene-index.miracl-v1.0-fr-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-fr-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language fr -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-fr & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-fr-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-fr-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-fr.bm25.topics.miracl-v1.0-fr-dev.txt \ -bm25 -hits 100 -language fr -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-fr.md b/docs/regressions/regressions-miracl-v1.0-fr.md index 998a606170..4057dcd7d0 100644 --- a/docs/regressions/regressions-miracl-v1.0-fr.md +++ b/docs/regressions/regressions-miracl-v1.0-fr.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-fr \ - -index indexes/lucene-index.miracl-v1.0-fr/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-fr/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language fr \ >& logs/log.miracl-v1.0-fr & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-fr/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-fr-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-fr.bm25.topics.miracl-v1.0-fr-dev.txt \ -bm25 -hits 100 -language fr & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-hi-aca.md b/docs/regressions/regressions-miracl-v1.0-hi-aca.md index 419939deb3..96cb98c827 100644 --- a/docs/regressions/regressions-miracl-v1.0-hi-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-hi-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-hi \ - -index indexes/lucene-index.miracl-v1.0-hi-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-hi-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language hi -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-hi & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-hi-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-hi-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-hi.bm25.topics.miracl-v1.0-hi-dev.txt \ -bm25 -hits 100 -language hi -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-hi.md b/docs/regressions/regressions-miracl-v1.0-hi.md index 383df69b2f..b56ab228c3 100644 --- a/docs/regressions/regressions-miracl-v1.0-hi.md +++ b/docs/regressions/regressions-miracl-v1.0-hi.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-hi \ - -index indexes/lucene-index.miracl-v1.0-hi/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-hi/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language hi \ >& logs/log.miracl-v1.0-hi & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-hi/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-hi-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-hi.bm25.topics.miracl-v1.0-hi-dev.txt \ -bm25 -hits 100 -language hi & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-id-aca.md b/docs/regressions/regressions-miracl-v1.0-id-aca.md index 043dbac525..daf70565cf 100644 --- a/docs/regressions/regressions-miracl-v1.0-id-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-id-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-id \ - -index indexes/lucene-index.miracl-v1.0-id-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-id-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language id -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-id & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-id-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-id-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-id.bm25.topics.miracl-v1.0-id-dev.txt \ -bm25 -hits 100 -language id -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-id.md b/docs/regressions/regressions-miracl-v1.0-id.md index 41cc08705a..fa3f1f6b7b 100644 --- a/docs/regressions/regressions-miracl-v1.0-id.md +++ b/docs/regressions/regressions-miracl-v1.0-id.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-id \ - -index indexes/lucene-index.miracl-v1.0-id/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-id/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language id \ >& logs/log.miracl-v1.0-id & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-id/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-id-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-id.bm25.topics.miracl-v1.0-id-dev.txt \ -bm25 -hits 100 -language id & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-ja-aca.md b/docs/regressions/regressions-miracl-v1.0-ja-aca.md index be267a0565..fdd9235030 100644 --- a/docs/regressions/regressions-miracl-v1.0-ja-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-ja-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-ja \ - -index indexes/lucene-index.miracl-v1.0-ja-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-ja-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ja -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-ja & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-ja-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-ja-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-ja.bm25.topics.miracl-v1.0-ja-dev.txt \ -bm25 -hits 100 -language ja -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-ja.md b/docs/regressions/regressions-miracl-v1.0-ja.md index 5024c8108d..44b647c6b5 100644 --- a/docs/regressions/regressions-miracl-v1.0-ja.md +++ b/docs/regressions/regressions-miracl-v1.0-ja.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-ja \ - -index indexes/lucene-index.miracl-v1.0-ja/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-ja/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ja \ >& logs/log.miracl-v1.0-ja & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-ja/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-ja-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-ja.bm25.topics.miracl-v1.0-ja-dev.txt \ -bm25 -hits 100 -language ja & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-ko-aca.md b/docs/regressions/regressions-miracl-v1.0-ko-aca.md index f9a38ba673..58fb048dfe 100644 --- a/docs/regressions/regressions-miracl-v1.0-ko-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-ko-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-ko \ - -index indexes/lucene-index.miracl-v1.0-ko-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-ko-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ko -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-ko & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-ko-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-ko-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-ko.bm25.topics.miracl-v1.0-ko-dev.txt \ -bm25 -hits 100 -language ko -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-ko.md b/docs/regressions/regressions-miracl-v1.0-ko.md index d419b53024..9e3d7e358b 100644 --- a/docs/regressions/regressions-miracl-v1.0-ko.md +++ b/docs/regressions/regressions-miracl-v1.0-ko.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-ko \ - -index indexes/lucene-index.miracl-v1.0-ko/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-ko/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ko \ >& logs/log.miracl-v1.0-ko & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-ko/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-ko-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-ko.bm25.topics.miracl-v1.0-ko-dev.txt \ -bm25 -hits 100 -language ko & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-ru-aca.md b/docs/regressions/regressions-miracl-v1.0-ru-aca.md index 41c7d8d185..64fce8c89d 100644 --- a/docs/regressions/regressions-miracl-v1.0-ru-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-ru-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-ru \ - -index indexes/lucene-index.miracl-v1.0-ru-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-ru-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ru -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-ru & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-ru-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-ru-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-ru.bm25.topics.miracl-v1.0-ru-dev.txt \ -bm25 -hits 100 -language ru -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-ru.md b/docs/regressions/regressions-miracl-v1.0-ru.md index 1558891615..a1565c73b5 100644 --- a/docs/regressions/regressions-miracl-v1.0-ru.md +++ b/docs/regressions/regressions-miracl-v1.0-ru.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-ru \ - -index indexes/lucene-index.miracl-v1.0-ru/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-ru/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ru \ >& logs/log.miracl-v1.0-ru & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-ru/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-ru-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-ru.bm25.topics.miracl-v1.0-ru-dev.txt \ -bm25 -hits 100 -language ru & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-sw-aca.md b/docs/regressions/regressions-miracl-v1.0-sw-aca.md index a3af03e24e..b0d9a2c789 100644 --- a/docs/regressions/regressions-miracl-v1.0-sw-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-sw-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-sw \ - -index indexes/lucene-index.miracl-v1.0-sw-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-sw-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language sw -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-sw & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-sw-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-sw-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-sw.bm25.topics.miracl-v1.0-sw-dev.txt \ -bm25 -hits 100 -language sw -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-sw.md b/docs/regressions/regressions-miracl-v1.0-sw.md index 0627413438..65a72df61b 100644 --- a/docs/regressions/regressions-miracl-v1.0-sw.md +++ b/docs/regressions/regressions-miracl-v1.0-sw.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-sw \ - -index indexes/lucene-index.miracl-v1.0-sw/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-sw/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language sw \ >& logs/log.miracl-v1.0-sw & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-sw/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-sw-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-sw.bm25.topics.miracl-v1.0-sw-dev.txt \ -bm25 -hits 100 -language sw & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-te-aca.md b/docs/regressions/regressions-miracl-v1.0-te-aca.md index 7b88a6a527..35cc7fdb62 100644 --- a/docs/regressions/regressions-miracl-v1.0-te-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-te-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-te \ - -index indexes/lucene-index.miracl-v1.0-te-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-te-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language te -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-te & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-te-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-te-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-te.bm25.topics.miracl-v1.0-te-dev.txt \ -bm25 -hits 100 -language te -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-te.md b/docs/regressions/regressions-miracl-v1.0-te.md index ffff55a3c3..77674ec179 100644 --- a/docs/regressions/regressions-miracl-v1.0-te.md +++ b/docs/regressions/regressions-miracl-v1.0-te.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-te \ - -index indexes/lucene-index.miracl-v1.0-te/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-te/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language te \ >& logs/log.miracl-v1.0-te & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-te/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-te-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-te.bm25.topics.miracl-v1.0-te-dev.txt \ -bm25 -hits 100 -language te & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-th-aca.md b/docs/regressions/regressions-miracl-v1.0-th-aca.md index 0a371b7386..7815258dd7 100644 --- a/docs/regressions/regressions-miracl-v1.0-th-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-th-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-th \ - -index indexes/lucene-index.miracl-v1.0-th-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-th-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language th -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-th & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-th-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-th-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-th.bm25.topics.miracl-v1.0-th-dev.txt \ -bm25 -hits 100 -language th -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-th.md b/docs/regressions/regressions-miracl-v1.0-th.md index 74e4e2ffde..d62dea4bb9 100644 --- a/docs/regressions/regressions-miracl-v1.0-th.md +++ b/docs/regressions/regressions-miracl-v1.0-th.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-th \ - -index indexes/lucene-index.miracl-v1.0-th/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-th/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language th \ >& logs/log.miracl-v1.0-th & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-th/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-th-dev.tsv \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.miracl-v1.0-th.bm25.topics.miracl-v1.0-th-dev.txt \ -bm25 -hits 100 -language th & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-zh-aca.md b/docs/regressions/regressions-miracl-v1.0-zh-aca.md index e454b14191..7d883c7bb5 100644 --- a/docs/regressions/regressions-miracl-v1.0-zh-aca.md +++ b/docs/regressions/regressions-miracl-v1.0-zh-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-zh \ - -index indexes/lucene-index.miracl-v1.0-zh-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-zh-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language zh -useAutoCompositeAnalyzer \ >& logs/log.miracl-v1.0-zh & ``` @@ -38,7 +38,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-zh-aca/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-zh-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-zh.bm25.topics.miracl-v1.0-zh-dev.txt \ -bm25 -hits 100 -language zh -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-miracl-v1.0-zh.md b/docs/regressions/regressions-miracl-v1.0-zh.md index f2c2fe5696..03c3fd6f9c 100644 --- a/docs/regressions/regressions-miracl-v1.0-zh.md +++ b/docs/regressions/regressions-miracl-v1.0-zh.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/miracl-v1.0-zh \ - -index indexes/lucene-index.miracl-v1.0-zh/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.miracl-v1.0-zh/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language zh \ >& logs/log.miracl-v1.0-zh & ``` @@ -36,7 +36,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.miracl-v1.0-zh/ \ -topics tools/topics-and-qrels/topics.miracl-v1.0-zh-dev.tsv \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.miracl-v1.0-zh.bm25.topics.miracl-v1.0-zh-dev.txt \ -bm25 -hits 100 -language zh & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-ar-aca.md b/docs/regressions/regressions-mrtydi-v1.1-ar-aca.md index dd143bfae8..25c035200f 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-ar-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-ar-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-ar \ - -index indexes/lucene-index.mrtydi-v1.1-arabic-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-arabic-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ar -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-ar & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-arabic-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ar.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ar.bm25.topics.mrtydi-v1.1-ar.train.txt \ -bm25 -hits 100 -language ar -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-arabic-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ar.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ar.bm25.topics.mrtydi-v1.1-ar.dev.txt \ -bm25 -hits 100 -language ar -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-arabic-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ar.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ar.bm25.topics.mrtydi-v1.1-ar.test.txt \ -bm25 -hits 100 -language ar -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-ar.md b/docs/regressions/regressions-mrtydi-v1.1-ar.md index 6821c4144f..66d9522016 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-ar.md +++ b/docs/regressions/regressions-mrtydi-v1.1-ar.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-ar \ - -index indexes/lucene-index.mrtydi-v1.1-arabic/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-arabic/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ar \ >& logs/log.mrtydi-v1.1-ar & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-arabic/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ar.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ar.bm25.topics.mrtydi-v1.1-ar.train.txt \ -bm25 -hits 100 -language ar & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-arabic/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ar.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ar.bm25.topics.mrtydi-v1.1-ar.dev.txt \ -bm25 -hits 100 -language ar & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-arabic/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ar.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ar.bm25.topics.mrtydi-v1.1-ar.test.txt \ -bm25 -hits 100 -language ar & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-bn-aca.md b/docs/regressions/regressions-mrtydi-v1.1-bn-aca.md index e80fdeeac3..6ce5a273cf 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-bn-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-bn-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-bn \ - -index indexes/lucene-index.mrtydi-v1.1-bengali-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-bengali-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language bn -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-bn & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-bengali-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-bn.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-bn.bm25.topics.mrtydi-v1.1-bn.train.txt \ -bm25 -hits 100 -language bn -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-bengali-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-bn.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-bn.bm25.topics.mrtydi-v1.1-bn.dev.txt \ -bm25 -hits 100 -language bn -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-bengali-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-bn.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-bn.bm25.topics.mrtydi-v1.1-bn.test.txt \ -bm25 -hits 100 -language bn -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-bn.md b/docs/regressions/regressions-mrtydi-v1.1-bn.md index bc84a274c1..e26a60c164 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-bn.md +++ b/docs/regressions/regressions-mrtydi-v1.1-bn.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-bn \ - -index indexes/lucene-index.mrtydi-v1.1-bengali/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-bengali/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language bn \ >& logs/log.mrtydi-v1.1-bn & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-bengali/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-bn.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-bn.bm25.topics.mrtydi-v1.1-bn.train.txt \ -bm25 -hits 100 -language bn & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-bengali/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-bn.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-bn.bm25.topics.mrtydi-v1.1-bn.dev.txt \ -bm25 -hits 100 -language bn & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-bengali/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-bn.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-bn.bm25.topics.mrtydi-v1.1-bn.test.txt \ -bm25 -hits 100 -language bn & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-en-aca.md b/docs/regressions/regressions-mrtydi-v1.1-en-aca.md index 63ab786d5b..87693706c1 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-en-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-en-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-en \ - -index indexes/lucene-index.mrtydi-v1.1-english-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-english-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language en -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-en & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-english-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-en.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-en.bm25.topics.mrtydi-v1.1-en.train.txt \ -bm25 -hits 100 -language en -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-english-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-en.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-en.bm25.topics.mrtydi-v1.1-en.dev.txt \ -bm25 -hits 100 -language en -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-english-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-en.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-en.bm25.topics.mrtydi-v1.1-en.test.txt \ -bm25 -hits 100 -language en -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-en.md b/docs/regressions/regressions-mrtydi-v1.1-en.md index 51276c37d1..dcfdbcfaa1 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-en.md +++ b/docs/regressions/regressions-mrtydi-v1.1-en.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-en \ - -index indexes/lucene-index.mrtydi-v1.1-english/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-english/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language en \ >& logs/log.mrtydi-v1.1-en & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-english/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-en.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-en.bm25.topics.mrtydi-v1.1-en.train.txt \ -bm25 -hits 100 -language en & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-english/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-en.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-en.bm25.topics.mrtydi-v1.1-en.dev.txt \ -bm25 -hits 100 -language en & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-english/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-en.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-en.bm25.topics.mrtydi-v1.1-en.test.txt \ -bm25 -hits 100 -language en & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-fi-aca.md b/docs/regressions/regressions-mrtydi-v1.1-fi-aca.md index 8c5d566fbe..4ff002f970 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-fi-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-fi-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-fi \ - -index indexes/lucene-index.mrtydi-v1.1-finnish-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-finnish-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language fi -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-fi & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-finnish-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-fi.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-fi.bm25.topics.mrtydi-v1.1-fi.train.txt \ -bm25 -hits 100 -language fi -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-finnish-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-fi.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-fi.bm25.topics.mrtydi-v1.1-fi.dev.txt \ -bm25 -hits 100 -language fi -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-finnish-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-fi.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-fi.bm25.topics.mrtydi-v1.1-fi.test.txt \ -bm25 -hits 100 -language fi -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-fi.md b/docs/regressions/regressions-mrtydi-v1.1-fi.md index e1bcbc15c8..4c64f3ed15 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-fi.md +++ b/docs/regressions/regressions-mrtydi-v1.1-fi.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-fi \ - -index indexes/lucene-index.mrtydi-v1.1-finnish/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-finnish/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language fi \ >& logs/log.mrtydi-v1.1-fi & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-finnish/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-fi.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-fi.bm25.topics.mrtydi-v1.1-fi.train.txt \ -bm25 -hits 100 -language fi & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-finnish/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-fi.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-fi.bm25.topics.mrtydi-v1.1-fi.dev.txt \ -bm25 -hits 100 -language fi & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-finnish/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-fi.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-fi.bm25.topics.mrtydi-v1.1-fi.test.txt \ -bm25 -hits 100 -language fi & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-id-aca.md b/docs/regressions/regressions-mrtydi-v1.1-id-aca.md index 509d03d926..af8d44dbd0 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-id-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-id-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-id \ - -index indexes/lucene-index.mrtydi-v1.1-indonesian-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-indonesian-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language id -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-id & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-indonesian-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-id.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-id.bm25.topics.mrtydi-v1.1-id.train.txt \ -bm25 -hits 100 -language id -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-indonesian-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-id.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-id.bm25.topics.mrtydi-v1.1-id.dev.txt \ -bm25 -hits 100 -language id -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-indonesian-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-id.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-id.bm25.topics.mrtydi-v1.1-id.test.txt \ -bm25 -hits 100 -language id -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-id.md b/docs/regressions/regressions-mrtydi-v1.1-id.md index daeedaa4b7..ebd7a3ae0e 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-id.md +++ b/docs/regressions/regressions-mrtydi-v1.1-id.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-id \ - -index indexes/lucene-index.mrtydi-v1.1-indonesian/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-indonesian/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language id \ >& logs/log.mrtydi-v1.1-id & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-indonesian/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-id.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-id.bm25.topics.mrtydi-v1.1-id.train.txt \ -bm25 -hits 100 -language id & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-indonesian/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-id.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-id.bm25.topics.mrtydi-v1.1-id.dev.txt \ -bm25 -hits 100 -language id & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-indonesian/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-id.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-id.bm25.topics.mrtydi-v1.1-id.test.txt \ -bm25 -hits 100 -language id & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-ja-aca.md b/docs/regressions/regressions-mrtydi-v1.1-ja-aca.md index f18c76f702..a31a3e7b98 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-ja-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-ja-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-ja \ - -index indexes/lucene-index.mrtydi-v1.1-japanese-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-japanese-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ja -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-ja & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-japanese-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ja.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ja.bm25.topics.mrtydi-v1.1-ja.train.txt \ -bm25 -hits 100 -language ja -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-japanese-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ja.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ja.bm25.topics.mrtydi-v1.1-ja.dev.txt \ -bm25 -hits 100 -language ja -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-japanese-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ja.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ja.bm25.topics.mrtydi-v1.1-ja.test.txt \ -bm25 -hits 100 -language ja -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-ja.md b/docs/regressions/regressions-mrtydi-v1.1-ja.md index a1c67bcce4..8fa0004c62 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-ja.md +++ b/docs/regressions/regressions-mrtydi-v1.1-ja.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-ja \ - -index indexes/lucene-index.mrtydi-v1.1-japanese/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-japanese/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ja \ >& logs/log.mrtydi-v1.1-ja & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-japanese/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ja.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ja.bm25.topics.mrtydi-v1.1-ja.train.txt \ -bm25 -hits 100 -language ja & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-japanese/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ja.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ja.bm25.topics.mrtydi-v1.1-ja.dev.txt \ -bm25 -hits 100 -language ja & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-japanese/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ja.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ja.bm25.topics.mrtydi-v1.1-ja.test.txt \ -bm25 -hits 100 -language ja & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-ko-aca.md b/docs/regressions/regressions-mrtydi-v1.1-ko-aca.md index 6495187ad2..c3a7dc4ee1 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-ko-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-ko-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-ko \ - -index indexes/lucene-index.mrtydi-v1.1-korean-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-korean-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ko -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-ko & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-korean-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ko.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ko.bm25.topics.mrtydi-v1.1-ko.train.txt \ -bm25 -hits 100 -language ko -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-korean-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ko.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ko.bm25.topics.mrtydi-v1.1-ko.dev.txt \ -bm25 -hits 100 -language ko -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-korean-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ko.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ko.bm25.topics.mrtydi-v1.1-ko.test.txt \ -bm25 -hits 100 -language ko -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-ko.md b/docs/regressions/regressions-mrtydi-v1.1-ko.md index e1030d8814..abc6138672 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-ko.md +++ b/docs/regressions/regressions-mrtydi-v1.1-ko.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-ko \ - -index indexes/lucene-index.mrtydi-v1.1-korean/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-korean/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ko \ >& logs/log.mrtydi-v1.1-ko & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-korean/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ko.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ko.bm25.topics.mrtydi-v1.1-ko.train.txt \ -bm25 -hits 100 -language ko & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-korean/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ko.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ko.bm25.topics.mrtydi-v1.1-ko.dev.txt \ -bm25 -hits 100 -language ko & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-korean/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ko.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ko.bm25.topics.mrtydi-v1.1-ko.test.txt \ -bm25 -hits 100 -language ko & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-ru-aca.md b/docs/regressions/regressions-mrtydi-v1.1-ru-aca.md index c91c2c3225..eddde9fbe7 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-ru-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-ru-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-ru \ - -index indexes/lucene-index.mrtydi-v1.1-russian-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-russian-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ru -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-ru & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-russian-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ru.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ru.bm25.topics.mrtydi-v1.1-ru.train.txt \ -bm25 -hits 100 -language ru -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-russian-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ru.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ru.bm25.topics.mrtydi-v1.1-ru.dev.txt \ -bm25 -hits 100 -language ru -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-russian-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ru.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ru.bm25.topics.mrtydi-v1.1-ru.test.txt \ -bm25 -hits 100 -language ru -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-ru.md b/docs/regressions/regressions-mrtydi-v1.1-ru.md index 91b26dd682..635b55ee16 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-ru.md +++ b/docs/regressions/regressions-mrtydi-v1.1-ru.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-ru \ - -index indexes/lucene-index.mrtydi-v1.1-russian/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-russian/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language ru \ >& logs/log.mrtydi-v1.1-ru & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-russian/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ru.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ru.bm25.topics.mrtydi-v1.1-ru.train.txt \ -bm25 -hits 100 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-russian/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ru.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ru.bm25.topics.mrtydi-v1.1-ru.dev.txt \ -bm25 -hits 100 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-russian/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-ru.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-ru.bm25.topics.mrtydi-v1.1-ru.test.txt \ -bm25 -hits 100 -language ru & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-sw-aca.md b/docs/regressions/regressions-mrtydi-v1.1-sw-aca.md index 1c4a9fd4ad..dbe7a73221 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-sw-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-sw-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-sw \ - -index indexes/lucene-index.mrtydi-v1.1-swahili-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-swahili-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language sw -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-sw & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-swahili-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-sw.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-sw.bm25.topics.mrtydi-v1.1-sw.train.txt \ -bm25 -hits 100 -language sw -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-swahili-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-sw.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-sw.bm25.topics.mrtydi-v1.1-sw.dev.txt \ -bm25 -hits 100 -language sw -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-swahili-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-sw.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-sw.bm25.topics.mrtydi-v1.1-sw.test.txt \ -bm25 -hits 100 -language sw -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-sw.md b/docs/regressions/regressions-mrtydi-v1.1-sw.md index 35690ee565..012de12a30 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-sw.md +++ b/docs/regressions/regressions-mrtydi-v1.1-sw.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-sw \ - -index indexes/lucene-index.mrtydi-v1.1-swahili/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-swahili/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language sw \ >& logs/log.mrtydi-v1.1-sw & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-swahili/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-sw.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-sw.bm25.topics.mrtydi-v1.1-sw.train.txt \ -bm25 -hits 100 -language sw & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-swahili/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-sw.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-sw.bm25.topics.mrtydi-v1.1-sw.dev.txt \ -bm25 -hits 100 -language sw & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-swahili/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-sw.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-sw.bm25.topics.mrtydi-v1.1-sw.test.txt \ -bm25 -hits 100 -language sw & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-te-aca.md b/docs/regressions/regressions-mrtydi-v1.1-te-aca.md index 2735d94990..d48a86057f 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-te-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-te-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-te \ - -index indexes/lucene-index.mrtydi-v1.1-telugu-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-telugu-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language te -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-te & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-telugu-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-te.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-te.bm25.topics.mrtydi-v1.1-te.train.txt \ -bm25 -hits 100 -language te -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-telugu-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-te.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-te.bm25.topics.mrtydi-v1.1-te.dev.txt \ -bm25 -hits 100 -language te -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-telugu-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-te.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-te.bm25.topics.mrtydi-v1.1-te.test.txt \ -bm25 -hits 100 -language te -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-te.md b/docs/regressions/regressions-mrtydi-v1.1-te.md index bf39293cc4..29ee119622 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-te.md +++ b/docs/regressions/regressions-mrtydi-v1.1-te.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-te \ - -index indexes/lucene-index.mrtydi-v1.1-telugu/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-telugu/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language te \ >& logs/log.mrtydi-v1.1-te & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-telugu/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-te.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-te.bm25.topics.mrtydi-v1.1-te.train.txt \ -bm25 -hits 100 -language te & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-telugu/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-te.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-te.bm25.topics.mrtydi-v1.1-te.dev.txt \ -bm25 -hits 100 -language te & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-telugu/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-te.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-te.bm25.topics.mrtydi-v1.1-te.test.txt \ -bm25 -hits 100 -language te & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-th-aca.md b/docs/regressions/regressions-mrtydi-v1.1-th-aca.md index c2343b1cca..621cff98b1 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-th-aca.md +++ b/docs/regressions/regressions-mrtydi-v1.1-th-aca.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-th \ - -index indexes/lucene-index.mrtydi-v1.1-thai-aca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-thai-aca/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language th -useAutoCompositeAnalyzer \ >& logs/log.mrtydi-v1.1-th & ``` @@ -38,19 +38,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-thai-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-th.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-th.bm25.topics.mrtydi-v1.1-th.train.txt \ -bm25 -hits 100 -language th -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-thai-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-th.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-th.bm25.topics.mrtydi-v1.1-th.dev.txt \ -bm25 -hits 100 -language th -useAutoCompositeAnalyzer & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-thai-aca/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-th.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-th.bm25.topics.mrtydi-v1.1-th.test.txt \ -bm25 -hits 100 -language th -useAutoCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-mrtydi-v1.1-th.md b/docs/regressions/regressions-mrtydi-v1.1-th.md index 76b48cb6a8..6ba723345b 100644 --- a/docs/regressions/regressions-mrtydi-v1.1-th.md +++ b/docs/regressions/regressions-mrtydi-v1.1-th.md @@ -19,8 +19,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/mrtydi-v1.1-th \ - -index indexes/lucene-index.mrtydi-v1.1-thai/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.mrtydi-v1.1-thai/ \ -threads 1 -storePositions -storeDocvectors -storeRaw -language th \ >& logs/log.mrtydi-v1.1-th & ``` @@ -36,19 +36,19 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-thai/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-th.train.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-th.bm25.topics.mrtydi-v1.1-th.train.txt \ -bm25 -hits 100 -language th & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-thai/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-th.dev.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-th.bm25.topics.mrtydi-v1.1-th.dev.txt \ -bm25 -hits 100 -language th & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.mrtydi-v1.1-thai/ \ -topics tools/topics-and-qrels/topics.mrtydi-v1.1-th.test.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.mrtydi-v1.1-th.bm25.topics.mrtydi-v1.1-th.test.txt \ -bm25 -hits 100 -language th & ``` diff --git a/docs/regressions/regressions-msmarco-doc-ca.md b/docs/regressions/regressions-msmarco-doc-ca.md index 153683c489..3ef5a95422 100644 --- a/docs/regressions/regressions-msmarco-doc-ca.md +++ b/docs/regressions/regressions-msmarco-doc-ca.md @@ -22,8 +22,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc \ - -index indexes/lucene-index.msmarco-doc-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-ca/ \ -threads 7 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-doc & ``` @@ -44,7 +44,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-ca/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default.topics.msmarco-doc.dev.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-msmarco-doc-docTTTTTquery.md b/docs/regressions/regressions-msmarco-doc-docTTTTTquery.md index cc69c9affd..548f43611e 100644 --- a/docs/regressions/regressions-msmarco-doc-docTTTTTquery.md +++ b/docs/regressions/regressions-msmarco-doc-docTTTTTquery.md @@ -31,8 +31,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-docTTTTTquery \ - -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -threads 7 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-docTTTTTquery & ``` @@ -53,14 +53,14 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-default.topics.msmarco-doc.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-docTTTTTquery.bm25-tuned.topics.msmarco-doc.dev.txt \ -bm25 -bm25.k1 4.68 -bm25.b 0.87 & ``` diff --git a/docs/regressions/regressions-msmarco-doc-hgf-wp.md b/docs/regressions/regressions-msmarco-doc-hgf-wp.md index d6d1824788..e7b3398be2 100644 --- a/docs/regressions/regressions-msmarco-doc-hgf-wp.md +++ b/docs/regressions/regressions-msmarco-doc-hgf-wp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc \ - -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -threads 7 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased \ >& logs/log.msmarco-doc & ``` @@ -45,7 +45,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-hgf-wp/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default.topics.msmarco-doc.dev.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased & ``` diff --git a/docs/regressions/regressions-msmarco-doc-segmented-ca.md b/docs/regressions/regressions-msmarco-doc-segmented-ca.md index b24413db67..fa039dd768 100644 --- a/docs/regressions/regressions-msmarco-doc-segmented-ca.md +++ b/docs/regressions/regressions-msmarco-doc-segmented-ca.md @@ -33,8 +33,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented \ - -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-doc-segmented & ``` @@ -55,7 +55,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-ca/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default.topics.msmarco-doc.dev.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-msmarco-doc-segmented-docTTTTTquery.md b/docs/regressions/regressions-msmarco-doc-segmented-docTTTTTquery.md index 1286055c93..52581ef6b4 100644 --- a/docs/regressions/regressions-msmarco-doc-segmented-docTTTTTquery.md +++ b/docs/regressions/regressions-msmarco-doc-segmented-docTTTTTquery.md @@ -32,8 +32,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented-docTTTTTquery \ - -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-segmented-docTTTTTquery & ``` @@ -54,14 +54,14 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-default.topics.msmarco-doc.dev.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-docTTTTTquery.bm25-tuned.topics.msmarco-doc.dev.txt \ -bm25 -bm25.k1 2.56 -bm25.b 0.59 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-doc-segmented-unicoil-noexp.md b/docs/regressions/regressions-msmarco-doc-segmented-unicoil-noexp.md index 0e54ed5905..1ddf7ae125 100644 --- a/docs/regressions/regressions-msmarco-doc-segmented-unicoil-noexp.md +++ b/docs/regressions/regressions-msmarco-doc-segmented-unicoil-noexp.md @@ -56,8 +56,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-doc-segmented-unicoil-noexp \ - -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-doc-segmented-unicoil-noexp & ``` @@ -80,7 +80,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.unicoil-noexp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil-noexp.unicoil.topics.msmarco-doc.dev.unicoil-noexp.txt \ -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-doc-segmented-unicoil.md b/docs/regressions/regressions-msmarco-doc-segmented-unicoil.md index 51af407557..3cc3fa7bf7 100644 --- a/docs/regressions/regressions-msmarco-doc-segmented-unicoil.md +++ b/docs/regressions/regressions-msmarco-doc-segmented-unicoil.md @@ -56,8 +56,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-doc-segmented-unicoil \ - -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-doc-segmented-unicoil & ``` @@ -80,7 +80,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-unicoil/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.unicoil.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-unicoil.unicoil.topics.msmarco-doc.dev.unicoil.txt \ -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-doc-segmented-wp.md b/docs/regressions/regressions-msmarco-doc-segmented-wp.md index 6bff0d5618..12a1d55b14 100644 --- a/docs/regressions/regressions-msmarco-doc-segmented-wp.md +++ b/docs/regressions/regressions-msmarco-doc-segmented-wp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented-wp \ - -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-doc-segmented-wp & ``` @@ -46,7 +46,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented-wp/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented-wp.bm25-default.topics.msmarco-doc.dev.wp.txt \ -bm25 -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-doc-segmented.md b/docs/regressions/regressions-msmarco-doc-segmented.md index 8ee9c58c0a..3b94ecc741 100644 --- a/docs/regressions/regressions-msmarco-doc-segmented.md +++ b/docs/regressions/regressions-msmarco-doc-segmented.md @@ -32,8 +32,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-segmented \ - -index indexes/lucene-index.msmarco-doc-segmented/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-segmented/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc-segmented & ``` @@ -54,14 +54,14 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-default.topics.msmarco-doc.dev.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-segmented/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-segmented.bm25-tuned.topics.msmarco-doc.dev.txt \ -bm25 -bm25.k1 2.16 -bm25.b 0.61 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-doc-wp.md b/docs/regressions/regressions-msmarco-doc-wp.md index 14e11505ce..32590f3cb2 100644 --- a/docs/regressions/regressions-msmarco-doc-wp.md +++ b/docs/regressions/regressions-msmarco-doc-wp.md @@ -23,8 +23,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc-wp \ - -index indexes/lucene-index.msmarco-doc-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc-wp/ \ -threads 7 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-doc-wp & ``` @@ -45,7 +45,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc-wp/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc-wp.bm25-default.topics.msmarco-doc.dev.wp.txt \ -bm25 -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-doc.md b/docs/regressions/regressions-msmarco-doc.md index 7fc7802316..0be6153205 100644 --- a/docs/regressions/regressions-msmarco-doc.md +++ b/docs/regressions/regressions-msmarco-doc.md @@ -31,8 +31,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-doc \ - -index indexes/lucene-index.msmarco-doc/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-doc/ \ -threads 7 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-doc & ``` @@ -53,21 +53,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-default.topics.msmarco-doc.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned.topics.msmarco-doc.dev.txt \ -bm25 -bm25.k1 3.44 -bm25.b 0.87 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-doc/ \ -topics tools/topics-and-qrels/topics.msmarco-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-doc.bm25-tuned2.topics.msmarco-doc.dev.txt \ -bm25 -bm25.k1 4.46 -bm25.b 0.82 & ``` diff --git a/docs/regressions/regressions-msmarco-passage-bm25-b8.md b/docs/regressions/regressions-msmarco-passage-bm25-b8.md index b436fd24b1..3fe5425947 100644 --- a/docs/regressions/regressions-msmarco-passage-bm25-b8.md +++ b/docs/regressions/regressions-msmarco-passage-bm25-b8.md @@ -47,8 +47,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-bm25-b8 \ - -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -threads 9 -impact -pretokenized \ >& logs/log.msmarco-passage-bm25-b8 & ``` @@ -68,7 +68,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-bm25-b8/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-bm25-b8.bm25-b8.topics.msmarco-passage.dev-subset.txt \ -impact & ``` diff --git a/docs/regressions/regressions-msmarco-passage-ca.md b/docs/regressions/regressions-msmarco-passage-ca.md index 7d95d37bdd..5addf66318 100644 --- a/docs/regressions/regressions-msmarco-passage-ca.md +++ b/docs/regressions/regressions-msmarco-passage-ca.md @@ -22,8 +22,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-wp \ - -index indexes/lucene-index.msmarco-passage-ca/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-ca/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \ >& logs/log.msmarco-wp & ``` @@ -43,7 +43,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-ca/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer & ``` diff --git a/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-fw.md b/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-fw.md index 91a3bece3f..da74d908ab 100644 --- a/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-fw.md +++ b/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-fw.md @@ -49,8 +49,8 @@ Sample indexing command, applying inverted indexes to dense vectors using the "f target/appassembler/bin/IndexInvertedDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ - -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -generator InvertedDenseVectorDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -threads 16 -encoding fw -fw.q 40 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -70,9 +70,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchInvertedDenseVectors \ -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.fw-40/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-fw-40.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt \ - -topicfield vector -encoding fw -fw.q 40 -hits 1000 & + -topicField vector -encoding fw -fw.q 40 -hits 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-hnsw-onnx.md b/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-hnsw-onnx.md index bbcefaea81..a19e8abdd5 100644 --- a/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-hnsw-onnx.md +++ b/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-hnsw-onnx.md @@ -52,8 +52,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -73,9 +73,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-hnsw.topics.msmarco-passage.dev-subset.txt \ - -querygenerator VectorQueryGenerator -topicfield title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil & + -generator VectorQueryGenerator -topicField title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-hnsw.md b/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-hnsw.md index 6422f440d7..d813573d06 100644 --- a/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-hnsw.md +++ b/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-hnsw.md @@ -52,8 +52,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -73,9 +73,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-hnsw.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt \ - -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 & + -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-lexlsh.md b/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-lexlsh.md index b49b71feee..844536b206 100644 --- a/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-lexlsh.md +++ b/docs/regressions/regressions-msmarco-passage-cos-dpr-distil-lexlsh.md @@ -49,8 +49,8 @@ Sample indexing command, applying inverted indexes to dense vectors using the "L target/appassembler/bin/IndexInvertedDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-cos-dpr-distil \ - -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -generator InvertedDenseVectorDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -threads 16 -encoding lexlsh -lexlsh.b 600 \ >& logs/log.msmarco-passage-cos-dpr-distil & ``` @@ -70,9 +70,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchInvertedDenseVectors \ -index indexes/lucene-index.msmarco-passage-cos-dpr-distil.lexlsh-600/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-cos-dpr-distil.cos-dpr-distil-lexlsh-600.topics.msmarco-passage.dev-subset.cos-dpr-distil.jsonl.txt \ - -topicfield vector -encoding lexlsh -lexlsh.b 600 -hits 1000 & + -topicField vector -encoding lexlsh -lexlsh.b 600 -hits 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-msmarco-passage-deepimpact.md b/docs/regressions/regressions-msmarco-passage-deepimpact.md index 56a55a8a87..3c5fce3aba 100644 --- a/docs/regressions/regressions-msmarco-passage-deepimpact.md +++ b/docs/regressions/regressions-msmarco-passage-deepimpact.md @@ -51,8 +51,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-deepimpact \ - -index indexes/lucene-index.msmarco-passage-deepimpact/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-deepimpact/ \ -threads 16 -impact -pretokenized \ >& logs/log.msmarco-passage-deepimpact & ``` @@ -75,7 +75,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-deepimpact/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.deepimpact.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-deepimpact.deepimpact.topics.msmarco-passage.dev-subset.deepimpact.txt \ -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage-distill-splade-max.md b/docs/regressions/regressions-msmarco-passage-distill-splade-max.md index d28ff0291b..88246d1f13 100644 --- a/docs/regressions/regressions-msmarco-passage-distill-splade-max.md +++ b/docs/regressions/regressions-msmarco-passage-distill-splade-max.md @@ -52,8 +52,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-distill-splade-max \ - -index indexes/lucene-index.msmarco-passage-distill-splade-max/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-distill-splade-max/ \ -threads 16 -impact -pretokenized \ >& logs/log.msmarco-passage-distill-splade-max & ``` @@ -76,7 +76,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-distill-splade-max/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.distill-splade-max.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-distill-splade-max.distill-splade-max.topics.msmarco-passage.dev-subset.distill-splade-max.txt \ -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage-doc2query.md b/docs/regressions/regressions-msmarco-passage-doc2query.md index 6f02845ff9..046e9276cf 100644 --- a/docs/regressions/regressions-msmarco-passage-doc2query.md +++ b/docs/regressions/regressions-msmarco-passage-doc2query.md @@ -26,8 +26,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage-doc2query \ - -index indexes/lucene-index.msmarco-passage-doc2query/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-doc2query/ \ -threads 9 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-passage-doc2query & ``` @@ -48,14 +48,14 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-doc2query/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-doc2query.bm25-default.topics.msmarco-passage.dev-subset.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-doc2query/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-doc2query.bm25-tuned.topics.msmarco-passage.dev-subset.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 & ``` diff --git a/docs/regressions/regressions-msmarco-passage-docTTTTTquery.md b/docs/regressions/regressions-msmarco-passage-docTTTTTquery.md index 8045c517fc..38c98eac11 100644 --- a/docs/regressions/regressions-msmarco-passage-docTTTTTquery.md +++ b/docs/regressions/regressions-msmarco-passage-docTTTTTquery.md @@ -25,8 +25,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage-docTTTTTquery \ - -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -threads 18 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-passage-docTTTTTquery & ``` @@ -47,21 +47,21 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-default.topics.msmarco-passage.dev-subset.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned.topics.msmarco-passage.dev-subset.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-docTTTTTquery/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-docTTTTTquery.bm25-tuned2.topics.msmarco-passage.dev-subset.txt \ -bm25 -bm25.k1 2.18 -bm25.b 0.86 & ``` diff --git a/docs/regressions/regressions-msmarco-passage-hgf-wp.md b/docs/regressions/regressions-msmarco-passage-hgf-wp.md index d966562785..9565a46c67 100644 --- a/docs/regressions/regressions-msmarco-passage-hgf-wp.md +++ b/docs/regressions/regressions-msmarco-passage-hgf-wp.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-wp \ - -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased \ >& logs/log.msmarco-wp & ``` @@ -45,7 +45,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-hgf-wp/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt \ -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased & ``` diff --git a/docs/regressions/regressions-msmarco-passage-openai-ada2.md b/docs/regressions/regressions-msmarco-passage-openai-ada2.md index 8383635829..8bd6c97658 100644 --- a/docs/regressions/regressions-msmarco-passage-openai-ada2.md +++ b/docs/regressions/regressions-msmarco-passage-openai-ada2.md @@ -52,8 +52,8 @@ Sample indexing command, building HNSW indexes: target/appassembler/bin/IndexHnswDenseVectors \ -collection JsonDenseVectorCollection \ -input /path/to/msmarco-passage-openai-ada2 \ + -generator HnswDenseVectorDocumentGenerator \ -index indexes/lucene-hnsw.msmarco-passage-openai-ada2/ \ - -generator LuceneDenseVectorDocumentGenerator \ -threads 16 -M 16 -efC 100 -memorybuffer 65536 \ >& logs/log.msmarco-passage-openai-ada2 & ``` @@ -73,9 +73,9 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchHnswDenseVectors \ -index indexes/lucene-hnsw.msmarco-passage-openai-ada2/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.openai-ada2.jsonl.gz \ - -topicreader JsonIntVector \ + -topicReader JsonIntVector \ -output runs/run.msmarco-passage-openai-ada2.openai-ada2.topics.msmarco-passage.dev-subset.openai-ada2.jsonl.txt \ - -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 & + -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 & ``` Evaluation can be performed using `trec_eval`: diff --git a/docs/regressions/regressions-msmarco-passage-splade-distil-cocodenser-medium.md b/docs/regressions/regressions-msmarco-passage-splade-distil-cocodenser-medium.md index d4c1ab6f30..0d98d1fe6a 100644 --- a/docs/regressions/regressions-msmarco-passage-splade-distil-cocodenser-medium.md +++ b/docs/regressions/regressions-msmarco-passage-splade-distil-cocodenser-medium.md @@ -51,8 +51,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade_distil_cocodenser_medium \ - -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade_distil_cocodenser_medium & ``` @@ -75,7 +75,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade_distil_cocodenser_medium/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.splade_distil_cocodenser_medium.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade_distil_cocodenser_medium.splade_distil_cocodenser_medium.topics.msmarco-passage.dev-subset.splade_distil_cocodenser_medium.txt \ -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage-splade-pp-ed-onnx.md b/docs/regressions/regressions-msmarco-passage-splade-pp-ed-onnx.md index a338515672..88a5d2ea9c 100644 --- a/docs/regressions/regressions-msmarco-passage-splade-pp-ed-onnx.md +++ b/docs/regressions/regressions-msmarco-passage-splade-pp-ed-onnx.md @@ -52,8 +52,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-ed & ``` @@ -76,7 +76,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.splade-pp-ed.topics.msmarco-passage.dev-subset.txt \ -impact -pretokenized -encoder SpladePlusPlusEnsembleDistil & ``` diff --git a/docs/regressions/regressions-msmarco-passage-splade-pp-ed.md b/docs/regressions/regressions-msmarco-passage-splade-pp-ed.md index 2f78c4c7a6..b2f74f09b1 100644 --- a/docs/regressions/regressions-msmarco-passage-splade-pp-ed.md +++ b/docs/regressions/regressions-msmarco-passage-splade-pp-ed.md @@ -52,8 +52,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-ed & ``` @@ -76,7 +76,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-ed.splade-pp-ed.topics.msmarco-passage.dev-subset.splade-pp-ed.txt \ -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage-splade-pp-sd-onnx.md b/docs/regressions/regressions-msmarco-passage-splade-pp-sd-onnx.md index f9c008474d..f6a8ef16c0 100644 --- a/docs/regressions/regressions-msmarco-passage-splade-pp-sd-onnx.md +++ b/docs/regressions/regressions-msmarco-passage-splade-pp-sd-onnx.md @@ -52,8 +52,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-sd & ``` @@ -76,7 +76,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.splade-pp-sd.topics.msmarco-passage.dev-subset.txt \ -impact -pretokenized -encoder SpladePlusPlusSelfDistil & ``` diff --git a/docs/regressions/regressions-msmarco-passage-splade-pp-sd.md b/docs/regressions/regressions-msmarco-passage-splade-pp-sd.md index 6c2e7ade9d..fafc7b3459 100644 --- a/docs/regressions/regressions-msmarco-passage-splade-pp-sd.md +++ b/docs/regressions/regressions-msmarco-passage-splade-pp-sd.md @@ -52,8 +52,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-splade-pp-sd & ``` @@ -76,7 +76,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-splade-pp-sd.splade-pp-sd.topics.msmarco-passage.dev-subset.splade-pp-sd.txt \ -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage-unicoil-noexp.md b/docs/regressions/regressions-msmarco-passage-unicoil-noexp.md index eee979caaa..f3cb29c94c 100644 --- a/docs/regressions/regressions-msmarco-passage-unicoil-noexp.md +++ b/docs/regressions/regressions-msmarco-passage-unicoil-noexp.md @@ -55,8 +55,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-unicoil-noexp \ - -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-unicoil-noexp & ``` @@ -79,7 +79,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil-noexp/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.unicoil-noexp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil-noexp.unicoil-noexp.topics.msmarco-passage.dev-subset.unicoil-noexp.txt \ -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage-unicoil-tilde-expansion.md b/docs/regressions/regressions-msmarco-passage-unicoil-tilde-expansion.md index 7bf5573009..fc295d6e51 100644 --- a/docs/regressions/regressions-msmarco-passage-unicoil-tilde-expansion.md +++ b/docs/regressions/regressions-msmarco-passage-unicoil-tilde-expansion.md @@ -52,8 +52,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-unicoil-tilde-expansion \ - -index indexes/lucene-index.msmarco-passage-unicoil-tilde-expansion/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-unicoil-tilde-expansion/ \ -threads 16 -impact -pretokenized \ >& logs/log.msmarco-passage-unicoil-tilde-expansion & ``` @@ -76,7 +76,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil-tilde-expansion/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.unicoil-tilde-expansion.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil-tilde-expansion.unicoil-tilde-expansion.topics.msmarco-passage.dev-subset.unicoil-tilde-expansion.txt \ -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage-unicoil.md b/docs/regressions/regressions-msmarco-passage-unicoil.md index a7a41b374a..a75a9083cd 100644 --- a/docs/regressions/regressions-msmarco-passage-unicoil.md +++ b/docs/regressions/regressions-msmarco-passage-unicoil.md @@ -52,8 +52,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-passage-unicoil \ - -index indexes/lucene-index.msmarco-passage-unicoil/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-unicoil/ \ -threads 16 -impact -pretokenized -storeDocvectors \ >& logs/log.msmarco-passage-unicoil & ``` @@ -76,7 +76,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-unicoil/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.unicoil.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-unicoil.unicoil.topics.msmarco-passage.dev-subset.unicoil.txt \ -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage-wp.md b/docs/regressions/regressions-msmarco-passage-wp.md index e2c1472ebd..a167ead958 100644 --- a/docs/regressions/regressions-msmarco-passage-wp.md +++ b/docs/regressions/regressions-msmarco-passage-wp.md @@ -23,8 +23,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage-wp \ - -index indexes/lucene-index.msmarco-passage-wp/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage-wp/ \ -threads 9 -storePositions -storeDocvectors -storeRaw -pretokenized \ >& logs/log.msmarco-passage-wp & ``` @@ -44,7 +44,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage-wp/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.wp.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage-wp.bm25-default.topics.msmarco-passage.dev-subset.wp.txt \ -bm25 -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-passage.md b/docs/regressions/regressions-msmarco-passage.md index 1f50e4b2b0..21124f06b5 100644 --- a/docs/regressions/regressions-msmarco-passage.md +++ b/docs/regressions/regressions-msmarco-passage.md @@ -22,8 +22,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/msmarco-passage \ - -index indexes/lucene-index.msmarco-passage/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-passage/ \ -threads 9 -storePositions -storeDocvectors -storeRaw \ >& logs/log.msmarco-passage & ``` @@ -44,14 +44,14 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-passage/ \ -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-passage.bm25-tuned.topics.msmarco-passage.dev-subset.txt \ -bm25 -bm25.k1 0.82 -bm25.b 0.68 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-doc-d2q-t5.md b/docs/regressions/regressions-msmarco-v2-doc-d2q-t5.md index 14860aaf5b..9d47283646 100644 --- a/docs/regressions/regressions-msmarco-v2-doc-d2q-t5.md +++ b/docs/regressions/regressions-msmarco-v2-doc-d2q-t5.md @@ -22,8 +22,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2DocCollection \ -input /path/to/msmarco-v2-doc-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-doc-d2q-t5 & ``` @@ -43,13 +43,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-d2q-t5.bm25-default.topics.msmarco-v2-doc.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-d2q-t5/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev2.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-d2q-t5.bm25-default.topics.msmarco-v2-doc.dev2.txt \ -bm25 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-doc-segmented-d2q-t5.md b/docs/regressions/regressions-msmarco-v2-doc-segmented-d2q-t5.md index c53e80a500..886c187798 100644 --- a/docs/regressions/regressions-msmarco-v2-doc-segmented-d2q-t5.md +++ b/docs/regressions/regressions-msmarco-v2-doc-segmented-d2q-t5.md @@ -22,8 +22,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2DocCollection \ -input /path/to/msmarco-v2-doc-segmented-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-doc-segmented-d2q-t5 & ``` @@ -43,13 +43,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-d2q-t5.bm25-default.topics.msmarco-v2-doc.dev.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev2.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-d2q-t5.bm25-default.topics.msmarco-v2-doc.dev2.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-0shot-v2.md b/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-0shot-v2.md index cbff8cf47d..5c22c18b8e 100644 --- a/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-0shot-v2.md +++ b/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-0shot-v2.md @@ -66,8 +66,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-doc-segmented-unicoil-0shot-v2 \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-doc-segmented-unicoil-0shot-v2 & ``` @@ -89,13 +89,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-0shot-v2.unicoil-0shot.topics.msmarco-v2-doc.dev.unicoil.0shot.txt \ -parallelism 16 -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot-v2/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev2.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-0shot-v2.unicoil-0shot.topics.msmarco-v2-doc.dev2.unicoil.0shot.txt \ -parallelism 16 -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-0shot.md b/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-0shot.md index ded8d8a8e2..2dcc2dcc63 100644 --- a/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-0shot.md +++ b/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-0shot.md @@ -65,8 +65,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-doc-segmented-unicoil-0shot \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot/ \ -threads 24 -impact -pretokenized \ >& logs/log.msmarco-v2-doc-segmented-unicoil-0shot & ``` @@ -88,13 +88,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-0shot.unicoil-0shot.topics.msmarco-v2-doc.dev.unicoil.0shot.txt \ -parallelism 16 -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev2.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-0shot.unicoil-0shot.topics.msmarco-v2-doc.dev2.unicoil.0shot.txt \ -parallelism 16 -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.md b/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.md index 6413a4bbab..2f2137d3b3 100644 --- a/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.md +++ b/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.md @@ -66,8 +66,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2 \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2 & ``` @@ -89,13 +89,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.unicoil-noexp-0shot.topics.msmarco-v2-doc.dev.unicoil-noexp.0shot.txt \ -parallelism 16 -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev2.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-noexp-0shot-v2.unicoil-noexp-0shot.topics.msmarco-v2-doc.dev2.unicoil-noexp.0shot.txt \ -parallelism 16 -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-noexp-0shot.md b/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-noexp-0shot.md index 0ad1cc7d80..854afdecf7 100644 --- a/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-noexp-0shot.md +++ b/docs/regressions/regressions-msmarco-v2-doc-segmented-unicoil-noexp-0shot.md @@ -65,8 +65,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-doc-segmented-unicoil-noexp-0shot \ - -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot/ \ -threads 24 -impact -pretokenized \ >& logs/log.msmarco-v2-doc-segmented-unicoil-noexp-0shot & ``` @@ -88,13 +88,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-noexp-0shot.unicoil-noexp-0shot.topics.msmarco-v2-doc.dev.unicoil-noexp.0shot.txt \ -parallelism 16 -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev2.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented-unicoil-noexp-0shot.unicoil-noexp-0shot.topics.msmarco-v2-doc.dev2.unicoil-noexp.0shot.txt \ -parallelism 16 -impact -pretokenized -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-doc-segmented.md b/docs/regressions/regressions-msmarco-v2-doc-segmented.md index c5cda8da5e..f8422ccb06 100644 --- a/docs/regressions/regressions-msmarco-v2-doc-segmented.md +++ b/docs/regressions/regressions-msmarco-v2-doc-segmented.md @@ -23,8 +23,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2DocCollection \ -input /path/to/msmarco-v2-doc-segmented \ - -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-doc-segmented & ``` @@ -44,13 +44,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented.bm25-default.topics.msmarco-v2-doc.dev.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc-segmented/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev2.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc-segmented.bm25-default.topics.msmarco-v2-doc.dev2.txt \ -bm25 -hits 10000 -selectMaxPassage -selectMaxPassage.delimiter "#" -selectMaxPassage.hits 1000 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-doc.md b/docs/regressions/regressions-msmarco-v2-doc.md index a390f2835c..365d5a0f1a 100644 --- a/docs/regressions/regressions-msmarco-v2-doc.md +++ b/docs/regressions/regressions-msmarco-v2-doc.md @@ -23,8 +23,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2DocCollection \ -input /path/to/msmarco-v2-doc \ - -index indexes/lucene-index.msmarco-v2-doc/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-doc/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-doc & ``` @@ -44,13 +44,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc.bm25-default.topics.msmarco-v2-doc.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-doc/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-doc.dev2.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-doc.bm25-default.topics.msmarco-v2-doc.dev2.txt \ -bm25 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-passage-augmented-d2q-t5.md b/docs/regressions/regressions-msmarco-v2-passage-augmented-d2q-t5.md index bb6e446dc6..eb9e8ab9a6 100644 --- a/docs/regressions/regressions-msmarco-v2-passage-augmented-d2q-t5.md +++ b/docs/regressions/regressions-msmarco-v2-passage-augmented-d2q-t5.md @@ -22,8 +22,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-augmented-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-augmented-d2q-t5 & ``` @@ -42,13 +42,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented-d2q-t5.bm25-default.topics.msmarco-v2-passage.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented-d2q-t5/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev2.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented-d2q-t5.bm25-default.topics.msmarco-v2-passage.dev2.txt \ -bm25 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-passage-augmented.md b/docs/regressions/regressions-msmarco-v2-passage-augmented.md index 3d8e29bb40..f7a6267819 100644 --- a/docs/regressions/regressions-msmarco-v2-passage-augmented.md +++ b/docs/regressions/regressions-msmarco-v2-passage-augmented.md @@ -23,8 +23,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-augmented \ - -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-augmented & ``` @@ -44,13 +44,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented.bm25-default.topics.msmarco-v2-passage.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-augmented/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev2.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-augmented.bm25-default.topics.msmarco-v2-passage.dev2.txt \ -bm25 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-passage-d2q-t5.md b/docs/regressions/regressions-msmarco-v2-passage-d2q-t5.md index 01c6ea8426..c99905c224 100644 --- a/docs/regressions/regressions-msmarco-v2-passage-d2q-t5.md +++ b/docs/regressions/regressions-msmarco-v2-passage-d2q-t5.md @@ -22,8 +22,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage-d2q-t5 \ - -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage-d2q-t5 & ``` @@ -42,13 +42,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-d2q-t5.bm25-default.topics.msmarco-v2-passage.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-d2q-t5/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev2.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-d2q-t5.bm25-default.topics.msmarco-v2-passage.dev2.txt \ -bm25 & ``` diff --git a/docs/regressions/regressions-msmarco-v2-passage-splade-pp-ed.md b/docs/regressions/regressions-msmarco-v2-passage-splade-pp-ed.md index f3905dafac..1420ade49e 100644 --- a/docs/regressions/regressions-msmarco-v2-passage-splade-pp-ed.md +++ b/docs/regressions/regressions-msmarco-v2-passage-splade-pp-ed.md @@ -53,8 +53,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-splade-pp-ed \ - -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-splade-pp-ed & ``` @@ -76,13 +76,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-ed.splade-pp-ed.topics.msmarco-v2-passage.dev.splade-pp-ed.txt \ -parallelism 16 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-ed/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev2.splade-pp-ed.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-ed.splade-pp-ed.topics.msmarco-v2-passage.dev2.splade-pp-ed.txt \ -parallelism 16 -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-v2-passage-splade-pp-sd.md b/docs/regressions/regressions-msmarco-v2-passage-splade-pp-sd.md index 783d5d88d9..87dcae7df2 100644 --- a/docs/regressions/regressions-msmarco-v2-passage-splade-pp-sd.md +++ b/docs/regressions/regressions-msmarco-v2-passage-splade-pp-sd.md @@ -53,8 +53,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-splade-pp-sd \ - -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-splade-pp-sd & ``` @@ -76,13 +76,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-sd.splade-pp-sd.topics.msmarco-v2-passage.dev.splade-pp-sd.txt \ -parallelism 16 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-splade-pp-sd/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev2.splade-pp-sd.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-splade-pp-sd.splade-pp-sd.topics.msmarco-v2-passage.dev2.splade-pp-sd.txt \ -parallelism 16 -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-v2-passage-unicoil-0shot.md b/docs/regressions/regressions-msmarco-v2-passage-unicoil-0shot.md index 7432ec1665..35f0c9673c 100644 --- a/docs/regressions/regressions-msmarco-v2-passage-unicoil-0shot.md +++ b/docs/regressions/regressions-msmarco-v2-passage-unicoil-0shot.md @@ -60,8 +60,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-unicoil-0shot \ - -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-unicoil-0shot & ``` @@ -83,13 +83,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-0shot.unicoil-0shot.topics.msmarco-v2-passage.dev.unicoil.0shot.txt \ -parallelism 16 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-0shot/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev2.unicoil.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-0shot.unicoil-0shot.topics.msmarco-v2-passage.dev2.unicoil.0shot.txt \ -parallelism 16 -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-v2-passage-unicoil-noexp-0shot.md b/docs/regressions/regressions-msmarco-v2-passage-unicoil-noexp-0shot.md index 892e41f2ef..e49da0272f 100644 --- a/docs/regressions/regressions-msmarco-v2-passage-unicoil-noexp-0shot.md +++ b/docs/regressions/regressions-msmarco-v2-passage-unicoil-noexp-0shot.md @@ -60,8 +60,8 @@ Sample indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/msmarco-v2-passage-unicoil-noexp-0shot \ - -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -threads 24 -impact -pretokenized -storeRaw \ >& logs/log.msmarco-v2-passage-unicoil-noexp-0shot & ``` @@ -83,13 +83,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-noexp-0shot.unicoil-noexp-0shot.topics.msmarco-v2-passage.dev.unicoil-noexp.0shot.txt \ -parallelism 16 -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage-unicoil-noexp-0shot/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev2.unicoil-noexp.0shot.tsv.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage-unicoil-noexp-0shot.unicoil-noexp-0shot.topics.msmarco-v2-passage.dev2.unicoil-noexp.0shot.txt \ -parallelism 16 -impact -pretokenized & ``` diff --git a/docs/regressions/regressions-msmarco-v2-passage.md b/docs/regressions/regressions-msmarco-v2-passage.md index 441070a898..474ae4c21f 100644 --- a/docs/regressions/regressions-msmarco-v2-passage.md +++ b/docs/regressions/regressions-msmarco-v2-passage.md @@ -23,8 +23,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MsMarcoV2PassageCollection \ -input /path/to/msmarco-v2-passage \ - -index indexes/lucene-index.msmarco-v2-passage/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.msmarco-v2-passage/ \ -threads 24 -storeRaw \ >& logs/log.msmarco-v2-passage & ``` @@ -44,13 +44,13 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage.bm25-default.topics.msmarco-v2-passage.dev.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.msmarco-v2-passage/ \ -topics tools/topics-and-qrels/topics.msmarco-v2-passage.dev2.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.msmarco-v2-passage.bm25-default.topics.msmarco-v2-passage.dev2.txt \ -bm25 & ``` diff --git a/docs/regressions/regressions-neuclir22-fa-dt-splade.md b/docs/regressions/regressions-neuclir22-fa-dt-splade.md index 8399a4daff..13e2f359bb 100644 --- a/docs/regressions/regressions-neuclir22-fa-dt-splade.md +++ b/docs/regressions/regressions-neuclir22-fa-dt-splade.md @@ -43,8 +43,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/neuclir22-fa-en-splade \ - -index indexes/lucene-index.neuclir22-fa-en-splade \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-fa-en-splade \ -threads 8 -impact -pretokenized -storeRaw \ >& logs/log.neuclir22-fa-en-splade & ``` @@ -59,57 +59,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade+rm3.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade+rm3.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade+rm3.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-neuclir22-fa-dt.md b/docs/regressions/regressions-neuclir22-fa-dt.md index f56df242a9..f0bf3b986b 100644 --- a/docs/regressions/regressions-neuclir22-fa-dt.md +++ b/docs/regressions/regressions-neuclir22-fa-dt.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-fa-en \ - -index indexes/lucene-index.neuclir22-fa-en \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-fa-en \ -threads 8 -storePositions -storeDocvectors -storeRaw \ >& logs/log.neuclir22-fa-en & ``` @@ -50,57 +50,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default.topics.neuclir22-en.original-title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default.topics.neuclir22-en.original-desc.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default.topics.neuclir22-en.original-desc_title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rm3.topics.neuclir22-en.original-title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rm3.topics.neuclir22-en.original-desc.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rm3.topics.neuclir22-en.original-desc_title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rocchio.topics.neuclir22-en.original-title.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rocchio.topics.neuclir22-en.original-desc.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-en.bm25-default+rocchio.topics.neuclir22-en.original-desc_title.txt \ -bm25 -rocchio & ``` diff --git a/docs/regressions/regressions-neuclir22-fa-qt-splade.md b/docs/regressions/regressions-neuclir22-fa-qt-splade.md index e6ca212a44..6792e79b17 100644 --- a/docs/regressions/regressions-neuclir22-fa-qt-splade.md +++ b/docs/regressions/regressions-neuclir22-fa-qt-splade.md @@ -43,8 +43,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/neuclir22-fa-splade \ - -index indexes/lucene-index.neuclir22-fa-splade \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-fa-splade \ -threads 8 -impact -pretokenized -storeRaw \ >& logs/log.neuclir22-fa-splade & ``` @@ -59,111 +59,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade.topics.neuclir22-fa.splade.ht-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade.topics.neuclir22-fa.splade.ht-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade.topics.neuclir22-fa.splade.ht-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade.topics.neuclir22-fa.splade.mt-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade.topics.neuclir22-fa.splade.mt-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade.topics.neuclir22-fa.splade.mt-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rm3.topics.neuclir22-fa.splade.ht-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rm3.topics.neuclir22-fa.splade.ht-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rm3.topics.neuclir22-fa.splade.ht-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rm3.topics.neuclir22-fa.splade.mt-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rm3.topics.neuclir22-fa.splade.mt-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rm3.topics.neuclir22-fa.splade.mt-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rocchio.topics.neuclir22-fa.splade.ht-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rocchio.topics.neuclir22-fa.splade.ht-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rocchio.topics.neuclir22-fa.splade.ht-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rocchio.topics.neuclir22-fa.splade.mt-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rocchio.topics.neuclir22-fa.splade.mt-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa-splade \ -topics tools/topics-and-qrels/topics.neuclir22-fa.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa-splade.splade+rocchio.topics.neuclir22-fa.splade.mt-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-neuclir22-fa-qt.md b/docs/regressions/regressions-neuclir22-fa-qt.md index 3f26b5c701..f4cc8e3177 100644 --- a/docs/regressions/regressions-neuclir22-fa-qt.md +++ b/docs/regressions/regressions-neuclir22-fa-qt.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-fa \ - -index indexes/lucene-index.neuclir22-fa \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-fa \ -threads 8 -storePositions -storeDocvectors -storeRaw -language fa \ >& logs/log.neuclir22-fa & ``` @@ -50,111 +50,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.neuclir22-fa.ht-title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.neuclir22-fa.ht-desc.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.neuclir22-fa.ht-desc_title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.neuclir22-fa.mt-title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.neuclir22-fa.mt-desc.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default.topics.neuclir22-fa.mt-desc_title.txt \ -bm25 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.neuclir22-fa.ht-title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.neuclir22-fa.ht-desc.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.neuclir22-fa.ht-desc_title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.neuclir22-fa.mt-title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.neuclir22-fa.mt-desc.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rm3.topics.neuclir22-fa.mt-desc_title.txt \ -bm25 -rm3 -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.neuclir22-fa.ht-title.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.neuclir22-fa.ht-desc.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.neuclir22-fa.ht-desc_title.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.neuclir22-fa.mt-title.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.neuclir22-fa.mt-desc.txt \ -bm25 -rocchio -language fa & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-fa \ -topics tools/topics-and-qrels/topics.neuclir22-fa.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-fa.bm25-default+rocchio.topics.neuclir22-fa.mt-desc_title.txt \ -bm25 -rocchio -language fa & ``` diff --git a/docs/regressions/regressions-neuclir22-ru-dt-splade.md b/docs/regressions/regressions-neuclir22-ru-dt-splade.md index a38f7a151e..c72a5e4b47 100644 --- a/docs/regressions/regressions-neuclir22-ru-dt-splade.md +++ b/docs/regressions/regressions-neuclir22-ru-dt-splade.md @@ -43,8 +43,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/neuclir22-ru-en-splade \ - -index indexes/lucene-index.neuclir22-ru-en-splade \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-ru-en-splade \ -threads 8 -impact -pretokenized -storeRaw \ >& logs/log.neuclir22-ru-en-splade & ``` @@ -59,57 +59,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade+rm3.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade+rm3.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade+rm3.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-neuclir22-ru-dt.md b/docs/regressions/regressions-neuclir22-ru-dt.md index 4818e05d39..633858eeaa 100644 --- a/docs/regressions/regressions-neuclir22-ru-dt.md +++ b/docs/regressions/regressions-neuclir22-ru-dt.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-ru-en \ - -index indexes/lucene-index.neuclir22-ru-en \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-ru-en \ -threads 8 -storePositions -storeDocvectors -storeRaw \ >& logs/log.neuclir22-ru-en & ``` @@ -50,57 +50,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default.topics.neuclir22-en.original-title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default.topics.neuclir22-en.original-desc.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default.topics.neuclir22-en.original-desc_title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rm3.topics.neuclir22-en.original-title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rm3.topics.neuclir22-en.original-desc.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rm3.topics.neuclir22-en.original-desc_title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rocchio.topics.neuclir22-en.original-title.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rocchio.topics.neuclir22-en.original-desc.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-en.bm25-default+rocchio.topics.neuclir22-en.original-desc_title.txt \ -bm25 -rocchio & ``` diff --git a/docs/regressions/regressions-neuclir22-ru-qt-splade.md b/docs/regressions/regressions-neuclir22-ru-qt-splade.md index 9a5995e06a..990a0a90bc 100644 --- a/docs/regressions/regressions-neuclir22-ru-qt-splade.md +++ b/docs/regressions/regressions-neuclir22-ru-qt-splade.md @@ -43,8 +43,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/neuclir22-ru-splade \ - -index indexes/lucene-index.neuclir22-ru-splade \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-ru-splade \ -threads 8 -impact -pretokenized -storeRaw \ >& logs/log.neuclir22-ru-splade & ``` @@ -59,111 +59,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade.topics.neuclir22-ru.splade.ht-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade.topics.neuclir22-ru.splade.ht-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade.topics.neuclir22-ru.splade.ht-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade.topics.neuclir22-ru.splade.mt-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade.topics.neuclir22-ru.splade.mt-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade.topics.neuclir22-ru.splade.mt-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rm3.topics.neuclir22-ru.splade.ht-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rm3.topics.neuclir22-ru.splade.ht-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rm3.topics.neuclir22-ru.splade.ht-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rm3.topics.neuclir22-ru.splade.mt-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rm3.topics.neuclir22-ru.splade.mt-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rm3.topics.neuclir22-ru.splade.mt-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rocchio.topics.neuclir22-ru.splade.ht-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rocchio.topics.neuclir22-ru.splade.ht-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rocchio.topics.neuclir22-ru.splade.ht-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rocchio.topics.neuclir22-ru.splade.mt-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rocchio.topics.neuclir22-ru.splade.mt-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru-splade \ -topics tools/topics-and-qrels/topics.neuclir22-ru.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru-splade.splade+rocchio.topics.neuclir22-ru.splade.mt-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-neuclir22-ru-qt.md b/docs/regressions/regressions-neuclir22-ru-qt.md index 2038738267..e8bef1fe86 100644 --- a/docs/regressions/regressions-neuclir22-ru-qt.md +++ b/docs/regressions/regressions-neuclir22-ru-qt.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-ru \ - -index indexes/lucene-index.neuclir22-ru \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-ru \ -threads 8 -storePositions -storeDocvectors -storeRaw -language ru \ >& logs/log.neuclir22-ru & ``` @@ -50,111 +50,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.neuclir22-ru.ht-title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.neuclir22-ru.ht-desc.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.neuclir22-ru.ht-desc_title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.neuclir22-ru.mt-title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.neuclir22-ru.mt-desc.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default.topics.neuclir22-ru.mt-desc_title.txt \ -bm25 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.neuclir22-ru.ht-title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.neuclir22-ru.ht-desc.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.neuclir22-ru.ht-desc_title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.neuclir22-ru.mt-title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.neuclir22-ru.mt-desc.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rm3.topics.neuclir22-ru.mt-desc_title.txt \ -bm25 -rm3 -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.neuclir22-ru.ht-title.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.neuclir22-ru.ht-desc.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.neuclir22-ru.ht-desc_title.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.neuclir22-ru.mt-title.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.neuclir22-ru.mt-desc.txt \ -bm25 -rocchio -language ru & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-ru \ -topics tools/topics-and-qrels/topics.neuclir22-ru.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-ru.bm25-default+rocchio.topics.neuclir22-ru.mt-desc_title.txt \ -bm25 -rocchio -language ru & ``` diff --git a/docs/regressions/regressions-neuclir22-zh-dt-splade.md b/docs/regressions/regressions-neuclir22-zh-dt-splade.md index aa3cf8bae9..a3635df163 100644 --- a/docs/regressions/regressions-neuclir22-zh-dt-splade.md +++ b/docs/regressions/regressions-neuclir22-zh-dt-splade.md @@ -43,8 +43,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/neuclir22-zh-en-splade \ - -index indexes/lucene-index.neuclir22-zh-en-splade \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-zh-en-splade \ -threads 8 -impact -pretokenized -storeRaw \ >& logs/log.neuclir22-zh-en-splade & ``` @@ -59,57 +59,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade+rm3.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade+rm3.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade+rm3.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en-splade \ -topics tools/topics-and-qrels/topics.neuclir22-en.splade.original-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en-splade.splade+rocchio.topics.neuclir22-en.splade.original-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-neuclir22-zh-dt.md b/docs/regressions/regressions-neuclir22-zh-dt.md index 9805975e1f..f01af92c69 100644 --- a/docs/regressions/regressions-neuclir22-zh-dt.md +++ b/docs/regressions/regressions-neuclir22-zh-dt.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-zh-en \ - -index indexes/lucene-index.neuclir22-zh-en \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-zh-en \ -threads 8 -storePositions -storeDocvectors -storeRaw \ >& logs/log.neuclir22-zh-en & ``` @@ -50,57 +50,57 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default.topics.neuclir22-en.original-title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default.topics.neuclir22-en.original-desc.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default.topics.neuclir22-en.original-desc_title.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rm3.topics.neuclir22-en.original-title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rm3.topics.neuclir22-en.original-desc.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rm3.topics.neuclir22-en.original-desc_title.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rocchio.topics.neuclir22-en.original-title.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rocchio.topics.neuclir22-en.original-desc.txt \ -bm25 -rocchio & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-en \ -topics tools/topics-and-qrels/topics.neuclir22-en.original-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-en.bm25-default+rocchio.topics.neuclir22-en.original-desc_title.txt \ -bm25 -rocchio & ``` diff --git a/docs/regressions/regressions-neuclir22-zh-qt-splade.md b/docs/regressions/regressions-neuclir22-zh-qt-splade.md index 5523cec46f..b8404787a6 100644 --- a/docs/regressions/regressions-neuclir22-zh-qt-splade.md +++ b/docs/regressions/regressions-neuclir22-zh-qt-splade.md @@ -43,8 +43,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonVectorCollection \ -input /path/to/neuclir22-zh-splade \ - -index indexes/lucene-index.neuclir22-zh-splade \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-zh-splade \ -threads 8 -impact -pretokenized -storeRaw \ >& logs/log.neuclir22-zh-splade & ``` @@ -59,111 +59,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade.topics.neuclir22-zh.splade.ht-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade.topics.neuclir22-zh.splade.ht-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade.topics.neuclir22-zh.splade.ht-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade.topics.neuclir22-zh.splade.mt-title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade.topics.neuclir22-zh.splade.mt-desc.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade.topics.neuclir22-zh.splade.mt-desc_title.txt \ -impact -pretokenized & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rm3.topics.neuclir22-zh.splade.ht-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rm3.topics.neuclir22-zh.splade.ht-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rm3.topics.neuclir22-zh.splade.ht-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rm3.topics.neuclir22-zh.splade.mt-title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rm3.topics.neuclir22-zh.splade.mt-desc.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rm3.topics.neuclir22-zh.splade.mt-desc_title.txt \ -impact -pretokenized -rm3 -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rocchio.topics.neuclir22-zh.splade.ht-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rocchio.topics.neuclir22-zh.splade.ht-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.ht-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rocchio.topics.neuclir22-zh.splade.ht-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rocchio.topics.neuclir22-zh.splade.mt-title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-desc.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rocchio.topics.neuclir22-zh.splade.mt-desc.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh-splade \ -topics tools/topics-and-qrels/topics.neuclir22-zh.splade.mt-desc_title.txt.gz \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh-splade.splade+rocchio.topics.neuclir22-zh.splade.mt-desc_title.txt \ -impact -pretokenized -rocchio -collection JsonVectorCollection & ``` diff --git a/docs/regressions/regressions-neuclir22-zh-qt.md b/docs/regressions/regressions-neuclir22-zh-qt.md index 1da2ca80d0..0a5172813b 100644 --- a/docs/regressions/regressions-neuclir22-zh-qt.md +++ b/docs/regressions/regressions-neuclir22-zh-qt.md @@ -34,8 +34,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection NeuClirCollection \ -input /path/to/neuclir22-zh \ - -index indexes/lucene-index.neuclir22-zh \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.neuclir22-zh \ -threads 8 -storePositions -storeDocvectors -storeRaw -language zh \ >& logs/log.neuclir22-zh & ``` @@ -50,111 +50,111 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.neuclir22-zh.ht-title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.neuclir22-zh.ht-desc.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.neuclir22-zh.ht-desc_title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.neuclir22-zh.mt-title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.neuclir22-zh.mt-desc.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default.topics.neuclir22-zh.mt-desc_title.txt \ -bm25 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.neuclir22-zh.ht-title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.neuclir22-zh.ht-desc.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.neuclir22-zh.ht-desc_title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.neuclir22-zh.mt-title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.neuclir22-zh.mt-desc.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rm3.topics.neuclir22-zh.mt-desc_title.txt \ -bm25 -rm3 -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.neuclir22-zh.ht-title.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.neuclir22-zh.ht-desc.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.ht-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.neuclir22-zh.ht-desc_title.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.neuclir22-zh.mt-title.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-desc.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.neuclir22-zh.mt-desc.txt \ -bm25 -rocchio -language zh & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.neuclir22-zh \ -topics tools/topics-and-qrels/topics.neuclir22-zh.mt-desc_title.txt \ - -topicreader TsvInt \ + -topicReader TsvInt \ -output runs/run.neuclir22-zh.bm25-default+rocchio.topics.neuclir22-zh.mt-desc_title.txt \ -bm25 -rocchio -language zh & ``` diff --git a/docs/regressions/regressions-ntcir8-zh.md b/docs/regressions/regressions-ntcir8-zh.md index 69bf7cfc2b..b19962b723 100644 --- a/docs/regressions/regressions-ntcir8-zh.md +++ b/docs/regressions/regressions-ntcir8-zh.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection CleanTrecCollection \ -input /path/to/ntcir8-zh \ - -index indexes/lucene-index.ntcir8-zh/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.ntcir8-zh/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language zh -uniqueDocid -optimize \ >& logs/log.ntcir8-zh & ``` @@ -47,7 +47,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.ntcir8-zh/ \ -topics tools/topics-and-qrels/topics.ntcir8zh.eval.txt \ - -topicreader TsvString \ + -topicReader TsvString \ -output runs/run.ntcir8-zh.bm25.topics.ntcir8zh.eval.txt \ -bm25 -language zh & ``` diff --git a/docs/regressions/regressions-robust05.md b/docs/regressions/regressions-robust05.md index 80769da8b2..23540e421b 100644 --- a/docs/regressions/regressions-robust05.md +++ b/docs/regressions/regressions-robust05.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection TrecCollection \ -input /path/to/robust05 \ - -index indexes/lucene-index.robust05/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.robust05/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.robust05 & ``` @@ -44,42 +44,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.robust05/ \ -topics tools/topics-and-qrels/topics.robust05.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.robust05.bm25.topics.robust05.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.robust05/ \ -topics tools/topics-and-qrels/topics.robust05.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.robust05.bm25+rm3.topics.robust05.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.robust05/ \ -topics tools/topics-and-qrels/topics.robust05.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.robust05.bm25+ax.topics.robust05.txt \ -bm25 -axiom -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.robust05/ \ -topics tools/topics-and-qrels/topics.robust05.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.robust05.ql.topics.robust05.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.robust05/ \ -topics tools/topics-and-qrels/topics.robust05.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.robust05.ql+rm3.topics.robust05.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.robust05/ \ -topics tools/topics-and-qrels/topics.robust05.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.robust05.ql+ax.topics.robust05.txt \ -qld -axiom -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/docs/regressions/regressions-trec02-ar.md b/docs/regressions/regressions-trec02-ar.md index 485e993256..c4a1c4bf21 100644 --- a/docs/regressions/regressions-trec02-ar.md +++ b/docs/regressions/regressions-trec02-ar.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection CleanTrecCollection \ -input /path/to/trec02-ar \ - -index indexes/lucene-index.trec02-ar/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.trec02-ar/ \ -threads 16 -storePositions -storeDocvectors -storeRaw -language ar \ >& logs/log.trec02-ar & ``` @@ -47,7 +47,7 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.trec02-ar/ \ -topics tools/topics-and-qrels/topics.trec02ar-ar.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.trec02-ar.bm25.topics.trec02ar-ar.txt \ -bm25 -language ar & ``` diff --git a/docs/regressions/regressions-wiki-all-6-3-tamber-bm25.md b/docs/regressions/regressions-wiki-all-6-3-tamber-bm25.md index a2409dbf24..63c421ab3d 100644 --- a/docs/regressions/regressions-wiki-all-6-3-tamber-bm25.md +++ b/docs/regressions/regressions-wiki-all-6-3-tamber-bm25.md @@ -24,8 +24,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection MrTyDiCollection \ -input /path/to/wiki-all-6-3-tamber \ - -index indexes/lucene-index.wiki-all-6-3-tamber/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.wiki-all-6-3-tamber/ \ -threads 20 -storeRaw \ >& logs/log.wiki-all-6-3-tamber & ``` @@ -45,37 +45,37 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wiki-all-6-3-tamber/ \ -topics tools/topics-and-qrels/topics.dpr.nq.test.txt \ - -topicreader DprNq \ + -topicReader DprNq \ -output runs/run.wiki-all-6-3-tamber.bm25.topics.dpr.nq.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wiki-all-6-3-tamber/ \ -topics tools/topics-and-qrels/topics.dpr.trivia.test.txt \ - -topicreader DprNq \ + -topicReader DprNq \ -output runs/run.wiki-all-6-3-tamber.bm25.topics.dpr.trivia.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wiki-all-6-3-tamber/ \ -topics tools/topics-and-qrels/topics.dpr.squad.test.txt \ - -topicreader DprJsonl \ + -topicReader DprJsonl \ -output runs/run.wiki-all-6-3-tamber.bm25.topics.dpr.squad.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wiki-all-6-3-tamber/ \ -topics tools/topics-and-qrels/topics.dpr.wq.test.txt \ - -topicreader DprJsonl \ + -topicReader DprJsonl \ -output runs/run.wiki-all-6-3-tamber.bm25.topics.dpr.wq.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wiki-all-6-3-tamber/ \ -topics tools/topics-and-qrels/topics.dpr.curated.test.txt \ - -topicreader DprJsonl \ + -topicReader DprJsonl \ -output runs/run.wiki-all-6-3-tamber.bm25.topics.dpr.curated.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wiki-all-6-3-tamber/ \ -topics tools/topics-and-qrels/topics.nq.test.txt \ - -topicreader DprNq \ + -topicReader DprNq \ -output runs/run.wiki-all-6-3-tamber.bm25.topics.nq.test.txt \ -bm25 & ``` diff --git a/docs/regressions/regressions-wikipedia-dpr-100w-bm25.md b/docs/regressions/regressions-wikipedia-dpr-100w-bm25.md index d67511f275..d8c73ccba4 100644 --- a/docs/regressions/regressions-wikipedia-dpr-100w-bm25.md +++ b/docs/regressions/regressions-wikipedia-dpr-100w-bm25.md @@ -21,8 +21,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection JsonCollection \ -input /path/to/wikipedia-dpr-100w \ - -index indexes/lucene-index.wikipedia-dpr-100w/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.wikipedia-dpr-100w/ \ -threads 43 -storeRaw \ >& logs/log.wikipedia-dpr-100w & ``` @@ -42,37 +42,37 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wikipedia-dpr-100w/ \ -topics tools/topics-and-qrels/topics.dpr.nq.test.txt \ - -topicreader DprNq \ + -topicReader DprNq \ -output runs/run.wikipedia-dpr-100w.bm25.topics.dpr.nq.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wikipedia-dpr-100w/ \ -topics tools/topics-and-qrels/topics.dpr.trivia.test.txt \ - -topicreader DprNq \ + -topicReader DprNq \ -output runs/run.wikipedia-dpr-100w.bm25.topics.dpr.trivia.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wikipedia-dpr-100w/ \ -topics tools/topics-and-qrels/topics.dpr.squad.test.txt \ - -topicreader DprJsonl \ + -topicReader DprJsonl \ -output runs/run.wikipedia-dpr-100w.bm25.topics.dpr.squad.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wikipedia-dpr-100w/ \ -topics tools/topics-and-qrels/topics.dpr.wq.test.txt \ - -topicreader DprJsonl \ + -topicReader DprJsonl \ -output runs/run.wikipedia-dpr-100w.bm25.topics.dpr.wq.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wikipedia-dpr-100w/ \ -topics tools/topics-and-qrels/topics.dpr.curated.test.txt \ - -topicreader DprJsonl \ + -topicReader DprJsonl \ -output runs/run.wikipedia-dpr-100w.bm25.topics.dpr.curated.test.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wikipedia-dpr-100w/ \ -topics tools/topics-and-qrels/topics.nq.test.txt \ - -topicreader DprNq \ + -topicReader DprNq \ -output runs/run.wikipedia-dpr-100w.bm25.topics.nq.test.txt \ -bm25 & ``` diff --git a/docs/regressions/regressions-wt10g.md b/docs/regressions/regressions-wt10g.md index a98253d304..2f8e253742 100644 --- a/docs/regressions/regressions-wt10g.md +++ b/docs/regressions/regressions-wt10g.md @@ -20,8 +20,8 @@ Typical indexing command: target/appassembler/bin/IndexCollection \ -collection TrecwebCollection \ -input /path/to/wt10g \ - -index indexes/lucene-index.wt10g/ \ -generator DefaultLuceneDocumentGenerator \ + -index indexes/lucene-index.wt10g/ \ -threads 16 -storePositions -storeDocvectors -storeRaw \ >& logs/log.wt10g & ``` @@ -44,42 +44,42 @@ After indexing has completed, you should be able to perform retrieval as follows target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wt10g/ \ -topics tools/topics-and-qrels/topics.adhoc.451-550.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wt10g.bm25.topics.adhoc.451-550.txt \ -bm25 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wt10g/ \ -topics tools/topics-and-qrels/topics.adhoc.451-550.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wt10g.bm25+rm3.topics.adhoc.451-550.txt \ -bm25 -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wt10g/ \ -topics tools/topics-and-qrels/topics.adhoc.451-550.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wt10g.bm25+ax.topics.adhoc.451-550.txt \ -bm25 -axiom -axiom.beta 0.1 -axiom.deterministic -rerankCutoff 20 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wt10g/ \ -topics tools/topics-and-qrels/topics.adhoc.451-550.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wt10g.ql.topics.adhoc.451-550.txt \ -qld & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wt10g/ \ -topics tools/topics-and-qrels/topics.adhoc.451-550.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wt10g.ql+rm3.topics.adhoc.451-550.txt \ -qld -rm3 & target/appassembler/bin/SearchCollection \ -index indexes/lucene-index.wt10g/ \ -topics tools/topics-and-qrels/topics.adhoc.451-550.txt \ - -topicreader Trec \ + -topicReader Trec \ -output runs/run.wt10g.ql+ax.topics.adhoc.451-550.txt \ -qld -axiom -axiom.beta 0.1 -axiom.deterministic -rerankCutoff 20 & ``` diff --git a/src/main/java/io/anserini/analysis/AutoCompositeAnalyzer.java b/src/main/java/io/anserini/analysis/AutoCompositeAnalyzer.java index 99ccea3387..da61128664 100644 --- a/src/main/java/io/anserini/analysis/AutoCompositeAnalyzer.java +++ b/src/main/java/io/anserini/analysis/AutoCompositeAnalyzer.java @@ -26,7 +26,7 @@ import java.util.Map; public class AutoCompositeAnalyzer { - private static final Logger LOG = LogManager.getLogger(CompositeAnalyzer.class); + private static final Logger LOG = LogManager.getLogger(AutoCompositeAnalyzer.class); private static final Map tokenizerMap = new HashMap<>() { { diff --git a/src/main/java/io/anserini/collection/EpidemicQACollection.java b/src/main/java/io/anserini/collection/EpidemicQACollection.java index 298b3d6e4f..b302dc4db1 100644 --- a/src/main/java/io/anserini/collection/EpidemicQACollection.java +++ b/src/main/java/io/anserini/collection/EpidemicQACollection.java @@ -65,9 +65,7 @@ public class Segment extends FileSegment { public Segment(Path path) throws IOException { super(path); - this.bufferedReader = new BufferedReader(new InputStreamReader( - new FileInputStream(path.toString()))); - LOG.info("Path: " + path.toString()); + this.bufferedReader = new BufferedReader(new InputStreamReader(new FileInputStream(path.toString()))); } public Segment(BufferedReader bufferedReader) throws IOException { diff --git a/src/main/java/io/anserini/encoder/OnnxEncoder.java b/src/main/java/io/anserini/encoder/OnnxEncoder.java index 43b7478707..d653b5d06f 100644 --- a/src/main/java/io/anserini/encoder/OnnxEncoder.java +++ b/src/main/java/io/anserini/encoder/OnnxEncoder.java @@ -47,11 +47,9 @@ public abstract class OnnxEncoder { static protected Path getVocabPath(String vocabName, String vocabURL) throws IOException { File vocabFile = new File(getCacheDir(), vocabName); if (!vocabFile.exists()) { - System.out.println("Downloading vocab"); FileUtils.copyURLToFile(new URL(vocabURL), vocabFile); - } else { - System.out.println("Vocab already exists"); } + return vocabFile.toPath(); } @@ -66,11 +64,9 @@ static protected String getCacheDir() { static protected Path getModelPath(String modelName, String modelURL) throws IOException { File modelFile = new File(getCacheDir(), modelName); if (!modelFile.exists()) { - System.out.println("Downloading model"); FileUtils.copyURLToFile(new URL(modelURL), modelFile); - } else { - System.out.println("Model already exists"); } + return modelFile.toPath(); } @@ -95,7 +91,6 @@ public OnnxEncoder(String modelName, String modelURL, String vocabName, String v this.environment = OrtEnvironment.getEnvironment(); this.session = environment.createSession(getModelPath(modelName, modelURL).toString(), new OrtSession.SessionOptions()); - System.out.println("Model loaded."); } } diff --git a/src/main/java/io/anserini/index/IndexHnswDenseVectors.java b/src/main/java/io/anserini/index/IndexHnswDenseVectors.java index aac83e60cc..4cfdffc4b5 100644 --- a/src/main/java/io/anserini/index/IndexHnswDenseVectors.java +++ b/src/main/java/io/anserini/index/IndexHnswDenseVectors.java @@ -23,7 +23,6 @@ import io.anserini.index.generator.InvalidDocumentException; import io.anserini.index.generator.LuceneDocumentGenerator; import io.anserini.index.generator.SkippedDocumentException; -import org.apache.commons.io.FileUtils; import org.apache.commons.lang3.time.DurationFormatUtils; import org.apache.logging.log4j.Level; import org.apache.logging.log4j.LogManager; @@ -34,151 +33,77 @@ import org.apache.lucene.codecs.KnnVectorsWriter; import org.apache.lucene.codecs.lucene95.Lucene95Codec; import org.apache.lucene.codecs.lucene95.Lucene95HnswVectorsFormat; -import org.apache.lucene.document.Document; import org.apache.lucene.index.ConcurrentMergeScheduler; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.index.SegmentReadState; import org.apache.lucene.index.SegmentWriteState; -import org.apache.lucene.index.Term; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.kohsuke.args4j.CmdLineException; import org.kohsuke.args4j.CmdLineParser; +import org.kohsuke.args4j.Option; import org.kohsuke.args4j.OptionHandlerFilter; import org.kohsuke.args4j.ParserProperties; -import org.kohsuke.args4j.Option; -import org.kohsuke.args4j.spi.StringArrayOptionHandler; import java.io.File; import java.io.IOException; import java.nio.file.Files; import java.nio.file.Path; import java.nio.file.Paths; -import java.util.HashSet; import java.util.List; -import java.util.Set; import java.util.concurrent.Executors; import java.util.concurrent.ThreadPoolExecutor; import java.util.concurrent.TimeUnit; -import java.util.concurrent.atomic.AtomicLong; public final class IndexHnswDenseVectors { private static final Logger LOG = LogManager.getLogger(IndexHnswDenseVectors.class); public static final class Args { + @Option(name = "-collection", metaVar = "[class]", required = true, usage = "Collection class in io.anserini.collection.") + public String collectionClass; - // This is the name of the field in the Lucene document where the docid is stored. - public static final String ID = "id"; - - // This is the name of the field in the Lucene document that should be searched by default. - public static final String CONTENTS = "contents"; - - // This is the name of the field in the Lucene document where the raw document is stored. - public static final String RAW = "raw"; - - // This is the name of the field in the Lucene document where the vector document is stored. - public static final String VECTOR = "vector"; - - private static final int TIMEOUT = 600 * 1000; + @Option(name = "-input", metaVar = "[path]", required = true, usage = "Input collection.") + public String input; + + @Option(name = "-generator", metaVar = "[class]", usage = "Document generator class in io.anserini.index.generator.") + public String generatorClass = "HnswDenseVectorDocumentGenerator"; - // required arguments - @Option(name = "-M", metaVar = "[num]", required = true, - usage = "HNSW parameters M") + @Option(name = "-index", metaVar = "[path]", required = true, usage = "Index path.") + public String index; + + @Option(name = "-M", metaVar = "[num]", usage = "HNSW parameters M") public int M = 16; - @Option(name = "-efC", metaVar = "[num]", required = true, - usage = "HNSW parameters ef Construction") + @Option(name = "-efC", metaVar = "[num]", usage = "HNSW parameters ef Construction") public int efC = 100; - - @Option(name = "-input", metaVar = "[path]", required = true, - usage = "Location of input collection.") - public String input; - - @Option(name = "-threads", metaVar = "[num]", required = true, - usage = "Number of indexing threads.") - public int threads; - - @Option(name = "-collection", metaVar = "[class]", required = true, - usage = "Collection class in package 'io.anserini.collection'.") - public String collectionClass; - - @Option(name = "-generator", metaVar = "[class]", - usage = "Document generator class in package 'io.anserini.index.generator'.") - public String generatorClass = "DefaultLuceneDocumentGenerator"; - - // optional general arguments - - @Option(name = "-verbose", forbids = {"-quiet"}, - usage = "Enables verbose logging for each indexing thread; can be noisy if collection has many small file segments.") + + @Option(name = "-optimize", usage = "Optimizes index by merging into a single index segment.") + public boolean optimize = false; + + @Option(name = "-memorybuffer", metaVar = "[mb]", usage = "Memory buffer size in MB.") + public int memorybufferSize = 4096; + + @Option(name = "-storeVectors", usage = "Boolean switch to store raw raw vectors.") + public boolean storeVectors = false; + + @Option(name = "-threads", metaVar = "[num]", usage = "Number of indexing threads.") + public int threads = 4; + + @Option(name = "-verbose", forbids = {"-quiet"}, usage = "Enables verbose logging for each indexing thread.") public boolean verbose = false; - - @Option(name = "-quiet", forbids = {"-verbose"}, - usage = "Turns off all logging.") + + @Option(name = "-quiet", forbids = {"-verbose"}, usage = "Turns off all logging.") public boolean quiet = false; - - // optional arguments - - @Option(name = "-index", metaVar = "[path]", usage = "Index path.") - public String index; - - @Option(name = "-fields", handler = StringArrayOptionHandler.class, - usage = "List of fields to index (space separated), in addition to the default 'contents' field.") - public String[] fields = new String[]{}; - - @Option(name = "-storePositions", - usage = "Boolean switch to index store term positions; needed for phrase queries.") - public boolean storePositions = false; - - @Option(name = "-storeDocvectors", - usage = "Boolean switch to store document vectors; needed for (pseudo) relevance feedback.") - public boolean storeDocvectors = false; - - @Option(name = "-storeContents", - usage = "Boolean switch to store document contents.") - public boolean storeContents = false; - - @Option(name = "-storeRaw", - usage = "Boolean switch to store raw source documents.") - public boolean storeRaw = false; - - @Option(name = "-optimize", - usage = "Boolean switch to optimize index (i.e., force merge) into a single segment; costly for large collections.") - public boolean optimize = false; - - @Option(name = "-uniqueDocid", - usage = "Removes duplicate documents with the same docid during indexing. This significantly slows indexing throughput " + - "but may be needed for tweet collections since the streaming API might deliver a tweet multiple times.") - public boolean uniqueDocid = false; - - @Option(name = "-memorybuffer", metaVar = "[mb]", - usage = "Memory buffer size (in MB).") - public int memorybufferSize = 2048; - - @Option(name = "-whitelist", metaVar = "[file]", - usage = "File containing list of docids, one per line; only these docids will be indexed.") - public String whitelist = null; - - - // Sharding options - - @Option(name = "-shard.count", metaVar = "[n]", - usage = "Number of shards to partition the document collection into.") - public int shardCount = -1; - - @Option(name = "-shard.current", metaVar = "[n]", - usage = "The current shard number to generate (indexed from 0).") - public int shardCurrent = -1; - + } private final class LocalIndexerThread extends Thread { final private Path inputFile; final private IndexWriter writer; - final private DocumentCollection collection; - private FileSegment fileSegment; + final private DocumentCollection collection; - private LocalIndexerThread(IndexWriter writer, DocumentCollection collection, Path inputFile) { + private LocalIndexerThread(IndexWriter writer, DocumentCollection collection, Path inputFile) { this.writer = writer; this.collection = collection; this.inputFile = inputFile; @@ -186,10 +111,12 @@ private LocalIndexerThread(IndexWriter writer, DocumentCollection collection, Pa } @Override - @SuppressWarnings("unchecked") public void run() { + FileSegment segment = null; + try { - LuceneDocumentGenerator generator = (LuceneDocumentGenerator) + @SuppressWarnings("unchecked") + LuceneDocumentGenerator generator = (LuceneDocumentGenerator) generatorClass.getDeclaredConstructor(Args.class).newInstance(args); // We keep track of two separate counts: the total count of documents in this file segment (cnt), @@ -199,9 +126,7 @@ public void run() { int cnt = 0; int batch = 0; - FileSegment segment = collection.createFileSegment(inputFile); - // in order to call close() and clean up resources in case of exception - this.fileSegment = segment; + segment = collection.createFileSegment(inputFile); for (SourceDocument d : segment) { if (!d.indexable()) { @@ -209,9 +134,11 @@ public void run() { continue; } - Document doc; try { - doc = generator.createDocument(d); + writer.addDocument(generator.createDocument(d)); + + cnt++; + batch++; } catch (EmptyDocumentException e1) { counters.empty.incrementAndGet(); continue; @@ -223,19 +150,6 @@ public void run() { continue; } - if (whitelistDocids != null && !whitelistDocids.contains(d.id())) { - counters.skipped.incrementAndGet(); - continue; - } - - if (args.uniqueDocid) { - writer.updateDocument(new Term("id", d.id()), doc); - } else { - writer.addDocument(doc); - } - cnt++; - batch++; - // And the counts from this batch, reset batch counter. if (batch % 10000 == 0) { counters.indexed.addAndGet(batch); @@ -266,21 +180,17 @@ public void run() { } catch (Exception e) { LOG.error(Thread.currentThread().getName() + ": Unexpected Exception:", e); } finally { - if (fileSegment != null) { - fileSegment.close(); - } + segment.close(); } } } private final Args args; private final Path collectionPath; - private final Set whitelistDocids; - private final Class collectionClass; - private final Class generatorClass; - private final DocumentCollection collection; + private final Class> generatorClass; + private final DocumentCollection collection; private final Counters counters; - private Path indexPath; + private final Path indexPath; @SuppressWarnings("unchecked") public IndexHnswDenseVectors(Args args) throws Exception { @@ -305,17 +215,13 @@ public IndexHnswDenseVectors(Args args) throws Exception { LOG.info("CollectionClass: " + args.collectionClass); LOG.info("Generator: " + args.generatorClass); LOG.info("Threads: " + args.threads); - LOG.info("Store document \"contents\" field? " + args.storeContents); - LOG.info("Store document \"raw\" field? " + args.storeRaw); + LOG.info("Store document vectors? " + args.storeVectors); LOG.info("Optimize (merge segments)? " + args.optimize); - LOG.info("Whitelist: " + args.whitelist); LOG.info("Index path: " + args.index); - if (args.index != null) { - this.indexPath = Paths.get(args.index); - if (!Files.exists(this.indexPath)) { + this.indexPath = Paths.get(args.index); + if (!Files.exists(this.indexPath)) { Files.createDirectories(this.indexPath); - } } // Our documentation uses /path/to/foo as a convention: to make copy and paste of the commands work, we assume @@ -324,23 +230,17 @@ public IndexHnswDenseVectors(Args args) throws Exception { if (pathStr.startsWith("/path/to")) { pathStr = pathStr.replace("/path/to", "collections"); } - collectionPath = Paths.get(pathStr); + this.collectionPath = Paths.get(pathStr); if (!Files.exists(collectionPath) || !Files.isReadable(collectionPath) || !Files.isDirectory(collectionPath)) { - throw new RuntimeException("Document directory " + collectionPath.toString() + " does not exist or is not readable, please check the path"); + throw new RuntimeException("Invalid collection path " + collectionPath + "!"); } - this.generatorClass = Class.forName("io.anserini.index.generator." + args.generatorClass); - this.collectionClass = Class.forName("io.anserini.collection." + args.collectionClass); + Class> collectionClass = (Class>) + Class.forName("io.anserini.collection." + args.collectionClass); + this.collection = collectionClass.getConstructor(Path.class).newInstance(collectionPath); - // Initialize the collection. - collection = (DocumentCollection) this.collectionClass.getConstructor(Path.class).newInstance(collectionPath); - - if (args.whitelist != null) { - List lines = FileUtils.readLines(new File(args.whitelist), "utf-8"); - this.whitelistDocids = new HashSet<>(lines); - } else { - this.whitelistDocids = null; - } + this.generatorClass = (Class>) + Class.forName("io.anserini.index.generator." + args.generatorClass); this.counters = new Counters(); } @@ -378,44 +278,32 @@ public Counters run() throws IOException { final long start = System.nanoTime(); LOG.info("============ Indexing Collection ============"); - int numThreads = args.threads; - IndexWriter writer = null; - - // Used for LocalIndexThread - if (indexPath != null) { - final Directory dir = FSDirectory.open(indexPath); - final IndexWriterConfig config = new IndexWriterConfig().setCodec(new Lucene95Codec(){ - @Override - public KnnVectorsFormat getKnnVectorsFormatForField(String field) { - return new OpenAiDelegatingKnnVectorsFormat( - new Lucene95HnswVectorsFormat(args.M, args.efC), 4096); - } - }); - config.setOpenMode(IndexWriterConfig.OpenMode.CREATE); - config.setRAMBufferSizeMB(args.memorybufferSize); - config.setUseCompoundFile(false); - config.setMergeScheduler(new ConcurrentMergeScheduler()); - writer = new IndexWriter(dir, config); - } - - final ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(numThreads); - LOG.info("Thread pool with " + numThreads + " threads initialized."); - + final Directory dir = FSDirectory.open(indexPath); + final IndexWriterConfig config = new IndexWriterConfig().setCodec( + new Lucene95Codec() { + @Override + public KnnVectorsFormat getKnnVectorsFormatForField(String field) { + return new OpenAiDelegatingKnnVectorsFormat( + new Lucene95HnswVectorsFormat(args.M, args.efC), 4096); + } + }); + config.setOpenMode(IndexWriterConfig.OpenMode.CREATE); + config.setRAMBufferSizeMB(args.memorybufferSize); + config.setUseCompoundFile(false); + config.setMergeScheduler(new ConcurrentMergeScheduler()); + IndexWriter writer = new IndexWriter(dir, config); + + final ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(args.threads); + LOG.info("Thread pool with " + args.threads + " threads initialized."); LOG.info("Initializing collection in " + collectionPath.toString()); - List segmentPaths = collection.getSegmentPaths(); - // when we want sharding to be done - if (args.shardCount > 1) { - segmentPaths = collection.getSegmentPaths(args.shardCount, args.shardCurrent); - } + List segmentPaths = collection.getSegmentPaths(); final int segmentCnt = segmentPaths.size(); LOG.info(String.format("%,d %s found", segmentCnt, (segmentCnt == 1 ? "file" : "files" ))); LOG.info("Starting to index..."); - for (int i = 0; i < segmentCnt; i++) { - executor.execute(new LocalIndexerThread(writer, collection, (Path) segmentPaths.get(i))); - } + segmentPaths.forEach((segmentPath) -> executor.execute(new LocalIndexerThread(writer, collection, segmentPath))); executor.shutdown(); @@ -445,17 +333,13 @@ public KnnVectorsFormat getKnnVectorsFormatForField(String field) { // Do a final commit try { - if (writer != null) { - writer.commit(); - if (args.optimize) { - writer.forceMerge(1); - } + writer.commit(); + if (args.optimize) { + writer.forceMerge(1); } } finally { try { - if (writer != null) { - writer.close(); - } + writer.close(); } catch (IOException e) { // It is possible that this happens... but nothing much we can do at this point, // so just log the error and move on. diff --git a/src/main/java/io/anserini/index/IndexInvertedDenseVectors.java b/src/main/java/io/anserini/index/IndexInvertedDenseVectors.java index 4e580be848..54ed6b560d 100644 --- a/src/main/java/io/anserini/index/IndexInvertedDenseVectors.java +++ b/src/main/java/io/anserini/index/IndexInvertedDenseVectors.java @@ -61,9 +61,6 @@ public final class IndexInvertedDenseVectors { private static final Logger LOG = LogManager.getLogger(IndexInvertedDenseVectors.class); - public static final String FIELD_ID = "id"; - public static final String FIELD_VECTOR = "vector"; - public static final String FW = "fw"; public static final String LEXLSH = "lexlsh"; @@ -101,6 +98,9 @@ public static final class Args { @Option(name = "-lexlsh.b", metaVar = "[int]", usage = "LexLSH encoding: bucket count.") public int bucketCount = 300; + @Option(name = "-optimize", usage = "Optimizes index by merging into a single index segment.") + public boolean optimize = false; + @Option(name = "-memorybuffer", metaVar = "[mb]", usage = "Memory buffer size in MB.") public int memorybufferSize = 4096; @@ -112,9 +112,6 @@ public static final class Args { @Option(name = "-quiet", forbids = {"-verbose"}, usage = "Turns off all logging.") public boolean quiet = false; - - @Option(name = "-optimize", usage = "Optimizes index by merging into a single index segment.") - public boolean optimize = false; } private final class LocalIndexerThread extends Thread { @@ -249,8 +246,8 @@ public IndexInvertedDenseVectors(Args args) throws Exception { pathStr = pathStr.replace("/path/to", "collections"); } this.collectionPath = Paths.get(pathStr); - if (!Files.exists(collectionPath) || !Files.isReadable(collectionPath)) { - throw new RuntimeException("Collection path " + collectionPath + " does not exist or is not readable!"); + if (!Files.exists(collectionPath) || !Files.isReadable(collectionPath) || !Files.isDirectory(collectionPath)) { + throw new RuntimeException("Invalid collection path " + collectionPath + "!"); } Class> collectionClass = (Class>) @@ -277,7 +274,7 @@ public Counters run() throws IOException { } Map map = new HashMap<>(); - map.put(FIELD_VECTOR, vectorAnalyzer); + map.put(Constants.VECTOR, vectorAnalyzer); Analyzer analyzer = new PerFieldAnalyzerWrapper(new StandardAnalyzer(), map); final Directory dir = FSDirectory.open(indexPath); diff --git a/src/main/java/io/anserini/index/IndexReaderUtils.java b/src/main/java/io/anserini/index/IndexReaderUtils.java index 3fc468e96c..3a4e7fb926 100755 --- a/src/main/java/io/anserini/index/IndexReaderUtils.java +++ b/src/main/java/io/anserini/index/IndexReaderUtils.java @@ -777,17 +777,21 @@ public static String convertLuceneDocidToDocid(IndexReader reader, int docid) { * Returns index statistics. * * @param reader index reader + * @param field Lucene field * @return map from name of statistic to its value */ public static Map getIndexStats(IndexReader reader, String field) { Map indexStats = new HashMap<>(); try { - Terms terms = MultiTerms.getTerms(reader, field); indexStats.put("documents", reader.numDocs()); indexStats.put("non_empty_documents", reader.getDocCount(field)); - indexStats.put("unique_terms", terms.size()); indexStats.put("total_terms", reader.getSumTotalTermFreq(field)); + + Terms terms = MultiTerms.getTerms(reader, field); + if (terms != null) { + indexStats.put("unique_terms", terms.size()); + } } catch (IOException e) { // Eat any exceptions and just return null. return null; diff --git a/src/main/java/io/anserini/index/generator/LuceneDenseVectorDocumentGenerator.java b/src/main/java/io/anserini/index/generator/HnswDenseVectorDocumentGenerator.java similarity index 80% rename from src/main/java/io/anserini/index/generator/LuceneDenseVectorDocumentGenerator.java rename to src/main/java/io/anserini/index/generator/HnswDenseVectorDocumentGenerator.java index 38a7177fbf..958425361c 100644 --- a/src/main/java/io/anserini/index/generator/LuceneDenseVectorDocumentGenerator.java +++ b/src/main/java/io/anserini/index/generator/HnswDenseVectorDocumentGenerator.java @@ -39,10 +39,10 @@ * * @param type of the source document */ -public class LuceneDenseVectorDocumentGenerator implements LuceneDocumentGenerator { +public class HnswDenseVectorDocumentGenerator implements LuceneDocumentGenerator { protected IndexHnswDenseVectors.Args args; - protected LuceneDenseVectorDocumentGenerator() { + protected HnswDenseVectorDocumentGenerator() { } /** @@ -50,19 +50,20 @@ protected LuceneDenseVectorDocumentGenerator() { * * @param args configuration arguments */ - public LuceneDenseVectorDocumentGenerator(IndexHnswDenseVectors.Args args) { + public HnswDenseVectorDocumentGenerator(IndexHnswDenseVectors.Args args) { this.args = args; } - private float[] convertJsonArray(String vectorString) throws JsonMappingException, JsonProcessingException { + private float[] convertJsonArray(String vectorString) throws JsonProcessingException { ObjectMapper mapper = new ObjectMapper(); - ArrayList denseVector = mapper.readValue(vectorString, new TypeReference>(){}); + ArrayList denseVector = mapper.readValue(vectorString, new TypeReference<>(){}); + int length = denseVector.size(); float[] vector = new float[length]; - int i = 0; - for (Float f : denseVector) { - vector[i++] = f; + for (int i=0; i void runTopics() throws IOException { - TopicReader tr; SortedMap> topics = new TreeMap<>(); + for (String singleTopicsFile : args.topics) { Path topicsFilePath = Paths.get(singleTopicsFile); if (!Files.exists(topicsFilePath) || !Files.isRegularFile(topicsFilePath) || !Files.isReadable(topicsFilePath)) { throw new IllegalArgumentException("Topics file : " + topicsFilePath + " does not exist or is not a (readable) file."); } try { - tr = (TopicReader) Class.forName("io.anserini.search.topicreader." + args.topicReader + "TopicReader") + TopicReader tr = (TopicReader) Class + .forName(String.format("io.anserini.search.topicreader.%sTopicReader", args.topicReader)) .getConstructor(Path.class).newInstance(topicsFilePath); topics.putAll(tr.read()); } catch (Exception e) { @@ -366,16 +361,11 @@ public void runTopics() throws IOException { final ThreadPoolExecutor executor = (ThreadPoolExecutor) Executors.newFixedThreadPool(args.threads); - LOG.info("============ Launching Search Threads ============"); String outputPath = args.output; - if (args.skipexists && new File(outputPath).exists()) { - LOG.info("Run already exists, skipping: " + outputPath); - } else { - executor.execute(new SearcherThread<>(reader, topics, outputPath, runTag)); - executor.shutdown(); - } + executor.execute(new SearcherThread<>(reader, topics, outputPath, runTag)); + executor.shutdown(); try { // Wait for existing tasks to terminate @@ -390,12 +380,10 @@ public void runTopics() throws IOException { } public ScoredDocuments search(IndexSearcher searcher, float[] queryFloat) throws IOException { - KnnFloatVectorQuery query = new KnnFloatVectorQuery(IndexHnswDenseVectors.Args.VECTOR, queryFloat, args.efSearch); - - TopDocs rs = new TopDocs(new TotalHits(0, TotalHits.Relation.EQUAL_TO), new ScoreDoc[]{}); - rs = searcher.search(query, args.hits); - ScoredDocuments scoredDocs; - scoredDocs = ScoredDocuments.fromTopDocs(rs, searcher); + KnnFloatVectorQuery query = new KnnFloatVectorQuery(Constants.VECTOR, queryFloat, args.efSearch); + + TopDocs rs = searcher.search(query, args.hits, BREAK_SCORE_TIES_BY_DOCID, true); + ScoredDocuments scoredDocs = ScoredDocuments.fromTopDocs(rs, searcher); return scoredDocs; } @@ -411,14 +399,9 @@ public ScoredDocuments search(IndexSearcher searcher, String queryString) throws throw new IllegalArgumentException("Unable to load QueryGenerator: " + args.topicReader); } - // If fieldsMap isn't null, then it means that the -fields option is specified. In this case, we search across - // multiple fields with the associated boosts. - query = generator.buildQuery(IndexHnswDenseVectors.Args.VECTOR, queryString, args.efSearch); - - TopDocs rs = new TopDocs(new TotalHits(0, TotalHits.Relation.EQUAL_TO), new ScoreDoc[]{}); - rs = searcher.search(query, args.hits); - ScoredDocuments scoredDocs; - scoredDocs = ScoredDocuments.fromTopDocs(rs, searcher); + query = generator.buildQuery(Constants.VECTOR, queryString, args.efSearch); + TopDocs rs = searcher.search(query, args.hits, BREAK_SCORE_TIES_BY_DOCID, true); + ScoredDocuments scoredDocs = ScoredDocuments.fromTopDocs(rs, searcher); return scoredDocs; } diff --git a/src/main/java/io/anserini/search/SearchInvertedDenseVectors.java b/src/main/java/io/anserini/search/SearchInvertedDenseVectors.java index 868a2dbe9b..81c862e5b9 100644 --- a/src/main/java/io/anserini/search/SearchInvertedDenseVectors.java +++ b/src/main/java/io/anserini/search/SearchInvertedDenseVectors.java @@ -28,6 +28,9 @@ import org.apache.lucene.index.IndexReader; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; +import org.apache.lucene.search.Sort; +import org.apache.lucene.search.SortField; +import org.apache.lucene.search.TopDocs; import org.apache.lucene.search.TopScoreDocCollector; import org.apache.lucene.search.similarities.ClassicSimilarity; import org.apache.lucene.search.similarities.Similarity; @@ -67,6 +70,11 @@ * Main entry point for inverted dense vector search. */ public final class SearchInvertedDenseVectors implements Closeable { + // These are the default tie-breaking rules for documents that end up with the same score with respect to a query. + // For most collections, docids are strings, and we break ties by lexicographic sort order. + public static final Sort BREAK_SCORE_TIES_BY_DOCID = + new Sort(SortField.FIELD_SCORE, new SortField(Constants.ID, SortField.Type.STRING_VAL)); + private static final Logger LOG = LogManager.getLogger(SearchInvertedDenseVectors.class); public static class Args { @@ -79,12 +87,11 @@ public static class Args { @Option(name = "-output", metaVar = "[file]", usage = "output file") public String output; - @Option(name = "-topicreader", usage = "TopicReader to use.") + @Option(name = "-topicReader", usage = "TopicReader to use.") public String topicReader; - @Option(name = "-topicfield", usage = "Which field of the query should be used, default \"title\"." + - " For TREC ad hoc topics, description or narrative can be used.") - public String topicfield = "title"; + @Option(name = "-topicField", usage = "Which field of topic should be used as the query.") + public String topicField = "title"; @Option(name = "-encoding", metaVar = "[word]", required = true, usage = "encoding must be one of {fw, lexlsh}") public String encoding; @@ -124,9 +131,6 @@ public static class Args { @Option(name = "-removedups", usage = "Remove duplicate docids when writing final run output.") public Boolean removedups = false; - @Option(name = "-skipexists", usage = "When enabled, will skip if the run file exists") - public Boolean skipexists = false; - @Option(name = "-hits", metaVar = "[number]", required = false, usage = "max number of hits to return") public int hits = 1000; @@ -163,7 +167,7 @@ public static class Args { @Option(name = "-selectMaxPassage.hits", metaVar = "[int]", usage = "Maximum number of hits to return per topic after segment id removal. " + - "Note that this is different from '-hits', which specifies the number of hits including the segment id. ") + "Note that this is different from '-hits', which specifies the number of hits including the segment id.") public int selectMaxPassage_hits = Integer.MAX_VALUE; } @@ -213,7 +217,7 @@ public void run() { executor.execute(() -> { // This is for holding the results. StringBuilder out = new StringBuilder(); - String queryString = entry.getValue().get(args.topicfield); + String queryString = entry.getValue().get(args.topicField); ScoredDocuments docs; try { docs = search(this.searcher, queryString); @@ -369,15 +373,9 @@ public void runTopics() { similarity = new ClassicSimilarity(); } String outputPath = args.output; - if (args.skipexists && new File(outputPath).exists()) { - LOG.info("Run already exists, skipping: " + outputPath); - } else { - executor.execute(new SearcherThread<>(reader, topics, outputPath, runTag, queryExecutor, similarity)); - executor.shutdown(); - if (queryExecutor != null) { - queryExecutor.shutdown(); - } - } + + executor.execute(new SearcherThread<>(reader, topics, outputPath, runTag, queryExecutor, similarity)); + executor.shutdown(); try { // Wait for existing tasks to terminate @@ -396,19 +394,15 @@ public void runTopics() { } public ScoredDocuments search(IndexSearcher searcher, String queryString) throws IOException { - // If fieldsMap isn't null, then it means that the -fields option is specified. In this case, we search across - // multiple fields with the associated boosts. Query query = generator.buildQuery(queryString); + TopDocs results = searcher.search(query, args.hits, BREAK_SCORE_TIES_BY_DOCID, true); - TopScoreDocCollector results = TopScoreDocCollector.create(args.hits, Integer.MAX_VALUE); - searcher.search(query, results); - - return ScoredDocuments.fromTopDocs(results.topDocs(), searcher); + return ScoredDocuments.fromTopDocs(results, searcher); } public static void main(String[] args) throws Exception { Args searchArgs = new Args(); - CmdLineParser parser = new CmdLineParser(searchArgs, ParserProperties.defaults().withUsageWidth(100)); + CmdLineParser parser = new CmdLineParser(searchArgs, ParserProperties.defaults().withUsageWidth(120)); try { parser.parseArgument(args); diff --git a/src/main/java/io/anserini/search/query/InvertedDenseVectorQueryGenerator.java b/src/main/java/io/anserini/search/query/InvertedDenseVectorQueryGenerator.java index 89b0382cae..f85e2e9d81 100644 --- a/src/main/java/io/anserini/search/query/InvertedDenseVectorQueryGenerator.java +++ b/src/main/java/io/anserini/search/query/InvertedDenseVectorQueryGenerator.java @@ -24,6 +24,7 @@ import io.anserini.analysis.AnalyzerUtils; import io.anserini.analysis.fw.FakeWordsEncoderAnalyzer; import io.anserini.analysis.lexlsh.LexicalLshAnalyzer; +import io.anserini.index.Constants; import io.anserini.index.IndexInvertedDenseVectors; import io.anserini.search.SearchInvertedDenseVectors; import org.apache.lucene.analysis.Analyzer; @@ -74,7 +75,7 @@ public Query buildQuery(String queryString) throws JsonProcessingException { float cutoff = 0.999f; CommonTermsQuery simQuery = new CommonTermsQuery(SHOULD, SHOULD, cutoff); for (String token : AnalyzerUtils.analyze(vectorAnalyzer, queryText)) { - simQuery.add(new Term(IndexInvertedDenseVectors.FIELD_VECTOR, token)); + simQuery.add(new Term(Constants.VECTOR, token)); } return simQuery; } diff --git a/src/main/python/run_regression.py b/src/main/python/run_regression.py index dbf81a9187..b8cffe19a2 100644 --- a/src/main/python/run_regression.py +++ b/src/main/python/run_regression.py @@ -127,10 +127,10 @@ def construct_indexing_command(yaml_data, args): index_command = [ root_cmd, '-collection', yaml_data['collection_class'], - '-generator', yaml_data['generator_class'], - '-threads', str(threads), '-input', corpus_path, + '-generator', yaml_data['generator_class'], '-index', yaml_data['index_path'], + '-threads', str(threads), yaml_data['index_options'] ] @@ -147,7 +147,7 @@ def construct_search_commands(yaml_data): SEARCH_INVERTED_DENSE_COMMAND if model.get('type') == 'inverted-dense' else SEARCH_HNSW_COMMAND if model.get('type') == 'hnsw' else SEARCH_COMMAND, '-index', construct_index_path(yaml_data), '-topics', os.path.join('tools/topics-and-qrels', topic_set['path']), - '-topicreader', topic_set['topic_reader'] if 'topic_reader' in topic_set and topic_set['topic_reader'] else yaml_data['topic_reader'], + '-topicReader', topic_set['topic_reader'] if 'topic_reader' in topic_set and topic_set['topic_reader'] else yaml_data['topic_reader'], '-output', construct_runfile_path(yaml_data['corpus'], topic_set['id'], model['name']), model['params'] ] diff --git a/src/main/resources/regression/dl19-passage-cos-dpr-distil-fw.yaml b/src/main/resources/regression/dl19-passage-cos-dpr-distil-fw.yaml index 9e1896dc71..baf7a22423 100644 --- a/src/main/resources/regression/dl19-passage-cos-dpr-distil-fw.yaml +++ b/src/main/resources/regression/dl19-passage-cos-dpr-distil-fw.yaml @@ -57,7 +57,7 @@ models: - name: cos-dpr-distil-fw-40 display: cosDPR-distill type: inverted-dense - params: -topicfield vector -encoding fw -fw.q 40 -hits 1000 + params: -topicField vector -encoding fw -fw.q 40 -hits 1000 results: AP@1000: - 0.4271 diff --git a/src/main/resources/regression/dl19-passage-cos-dpr-distil-hnsw-onnx.yaml b/src/main/resources/regression/dl19-passage-cos-dpr-distil-hnsw-onnx.yaml index 2e86181ba7..416e8efc63 100644 --- a/src/main/resources/regression/dl19-passage-cos-dpr-distil-hnsw-onnx.yaml +++ b/src/main/resources/regression/dl19-passage-cos-dpr-distil-hnsw-onnx.yaml @@ -8,7 +8,7 @@ download_checksum: e20ffbc8b5e7f760af31298aefeaebbd index_path: indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 @@ -53,7 +53,7 @@ models: - name: cos-dpr-distil-hnsw display: cosDPR-distil type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil + params: -generator VectorQueryGenerator -topicField title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil results: AP@1000: - 0.458 diff --git a/src/main/resources/regression/dl19-passage-cos-dpr-distil-hnsw.yaml b/src/main/resources/regression/dl19-passage-cos-dpr-distil-hnsw.yaml index b727ca45a2..67abbbf149 100644 --- a/src/main/resources/regression/dl19-passage-cos-dpr-distil-hnsw.yaml +++ b/src/main/resources/regression/dl19-passage-cos-dpr-distil-hnsw.yaml @@ -8,7 +8,7 @@ download_checksum: e20ffbc8b5e7f760af31298aefeaebbd index_path: indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 @@ -53,7 +53,7 @@ models: - name: cos-dpr-distil-hnsw display: cosDPR-distil type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 + params: -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 results: AP@1000: - 0.458 diff --git a/src/main/resources/regression/dl19-passage-cos-dpr-distil-lexlsh.yaml b/src/main/resources/regression/dl19-passage-cos-dpr-distil-lexlsh.yaml index 053bdcae16..8e99c127c6 100644 --- a/src/main/resources/regression/dl19-passage-cos-dpr-distil-lexlsh.yaml +++ b/src/main/resources/regression/dl19-passage-cos-dpr-distil-lexlsh.yaml @@ -57,7 +57,7 @@ models: - name: cos-dpr-distil-lexlsh-600 display: cosDPR-distill type: inverted-dense - params: -topicfield vector -encoding lexlsh -lexlsh.b 600 -hits 1000 + params: -topicField vector -encoding lexlsh -lexlsh.b 600 -hits 1000 results: AP@1000: - 0.4118 diff --git a/src/main/resources/regression/dl19-passage-openai-ada2.yaml b/src/main/resources/regression/dl19-passage-openai-ada2.yaml index 85c214bb22..ea0701a5d0 100644 --- a/src/main/resources/regression/dl19-passage-openai-ada2.yaml +++ b/src/main/resources/regression/dl19-passage-openai-ada2.yaml @@ -8,7 +8,7 @@ download_checksum: a4d843d522ff3a3af7edbee789a63402 index_path: indexes/lucene-hnsw.msmarco-passage-openai-ada2/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 -memorybuffer 65536 @@ -53,7 +53,7 @@ models: - name: openai-ada2 display: OpenAI-ada2 type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 + params: -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 results: AP@1000: - 0.479 diff --git a/src/main/resources/regression/dl20-passage-cos-dpr-distil-fw.yaml b/src/main/resources/regression/dl20-passage-cos-dpr-distil-fw.yaml index fb8737455a..9eb6b75f50 100644 --- a/src/main/resources/regression/dl20-passage-cos-dpr-distil-fw.yaml +++ b/src/main/resources/regression/dl20-passage-cos-dpr-distil-fw.yaml @@ -57,7 +57,7 @@ models: - name: cos-dpr-distil-fw-40 display: cosDPR-distill type: inverted-dense - params: -topicfield vector -encoding fw -fw.q 40 -hits 1000 + params: -topicField vector -encoding fw -fw.q 40 -hits 1000 results: AP@1000: - 0.4597 diff --git a/src/main/resources/regression/dl20-passage-cos-dpr-distil-hnsw-onnx.yaml b/src/main/resources/regression/dl20-passage-cos-dpr-distil-hnsw-onnx.yaml index 3cd457b2ee..15daab5abc 100644 --- a/src/main/resources/regression/dl20-passage-cos-dpr-distil-hnsw-onnx.yaml +++ b/src/main/resources/regression/dl20-passage-cos-dpr-distil-hnsw-onnx.yaml @@ -8,7 +8,7 @@ download_checksum: e20ffbc8b5e7f760af31298aefeaebbd index_path: indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 @@ -53,7 +53,7 @@ models: - name: cos-dpr-distil-hnsw display: cosDPR-distil type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil + params: -generator VectorQueryGenerator -topicField title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil results: AP@1000: - 0.482 diff --git a/src/main/resources/regression/dl20-passage-cos-dpr-distil-hnsw.yaml b/src/main/resources/regression/dl20-passage-cos-dpr-distil-hnsw.yaml index 5c4ddd872e..ba016059d6 100644 --- a/src/main/resources/regression/dl20-passage-cos-dpr-distil-hnsw.yaml +++ b/src/main/resources/regression/dl20-passage-cos-dpr-distil-hnsw.yaml @@ -8,7 +8,7 @@ download_checksum: e20ffbc8b5e7f760af31298aefeaebbd index_path: indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 @@ -53,7 +53,7 @@ models: - name: cos-dpr-distil-hnsw display: cosDPR-distil type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 + params: -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 results: AP@1000: - 0.482 diff --git a/src/main/resources/regression/dl20-passage-cos-dpr-distil-lexlsh.yaml b/src/main/resources/regression/dl20-passage-cos-dpr-distil-lexlsh.yaml index 8cd6132361..3f88b61ca6 100644 --- a/src/main/resources/regression/dl20-passage-cos-dpr-distil-lexlsh.yaml +++ b/src/main/resources/regression/dl20-passage-cos-dpr-distil-lexlsh.yaml @@ -57,7 +57,7 @@ models: - name: cos-dpr-distil-lexlsh-600 display: cosDPR-distill type: inverted-dense - params: -topicfield vector -encoding lexlsh -lexlsh.b 600 -hits 1000 + params: -topicField vector -encoding lexlsh -lexlsh.b 600 -hits 1000 results: AP@1000: - 0.4486 diff --git a/src/main/resources/regression/dl20-passage-openai-ada2.yaml b/src/main/resources/regression/dl20-passage-openai-ada2.yaml index be195093d3..e151b4f91b 100644 --- a/src/main/resources/regression/dl20-passage-openai-ada2.yaml +++ b/src/main/resources/regression/dl20-passage-openai-ada2.yaml @@ -8,7 +8,7 @@ download_checksum: a4d843d522ff3a3af7edbee789a63402 index_path: indexes/lucene-hnsw.msmarco-passage-openai-ada2/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 -memorybuffer 65536 @@ -53,7 +53,7 @@ models: - name: openai-ada2 display: OpenAI-ada2 type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 + params: -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 results: AP@1000: - 0.477 diff --git a/src/main/resources/regression/msmarco-passage-cos-dpr-distil-fw.yaml b/src/main/resources/regression/msmarco-passage-cos-dpr-distil-fw.yaml index f0e9bed0ba..180cde86f0 100644 --- a/src/main/resources/regression/msmarco-passage-cos-dpr-distil-fw.yaml +++ b/src/main/resources/regression/msmarco-passage-cos-dpr-distil-fw.yaml @@ -57,7 +57,7 @@ models: - name: cos-dpr-distil-fw-40 display: cosDPR-distill type: inverted-dense - params: -topicfield vector -encoding fw -fw.q 40 -hits 1000 + params: -topicField vector -encoding fw -fw.q 40 -hits 1000 results: AP@1000: - 0.3654 diff --git a/src/main/resources/regression/msmarco-passage-cos-dpr-distil-hnsw-onnx.yaml b/src/main/resources/regression/msmarco-passage-cos-dpr-distil-hnsw-onnx.yaml index d405ed98b6..b333652350 100644 --- a/src/main/resources/regression/msmarco-passage-cos-dpr-distil-hnsw-onnx.yaml +++ b/src/main/resources/regression/msmarco-passage-cos-dpr-distil-hnsw-onnx.yaml @@ -8,7 +8,7 @@ download_checksum: e20ffbc8b5e7f760af31298aefeaebbd index_path: indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 @@ -53,7 +53,7 @@ models: - name: cos-dpr-distil-hnsw display: cosDPR-distil type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil + params: -generator VectorQueryGenerator -topicField title -threads 16 -hits 1000 -efSearch 1000 -encoder CosDprDistil results: AP@1000: - 0.393 diff --git a/src/main/resources/regression/msmarco-passage-cos-dpr-distil-hnsw.yaml b/src/main/resources/regression/msmarco-passage-cos-dpr-distil-hnsw.yaml index 9464a90c38..65ffa3502d 100644 --- a/src/main/resources/regression/msmarco-passage-cos-dpr-distil-hnsw.yaml +++ b/src/main/resources/regression/msmarco-passage-cos-dpr-distil-hnsw.yaml @@ -8,7 +8,7 @@ download_checksum: e20ffbc8b5e7f760af31298aefeaebbd index_path: indexes/lucene-hnsw.msmarco-passage-cos-dpr-distil/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 @@ -53,7 +53,7 @@ models: - name: cos-dpr-distil-hnsw display: cosDPR-distil type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 + params: -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 results: AP@1000: - 0.393 diff --git a/src/main/resources/regression/msmarco-passage-cos-dpr-distil-lexlsh.yaml b/src/main/resources/regression/msmarco-passage-cos-dpr-distil-lexlsh.yaml index 57bdbf833e..7c1d5b8090 100644 --- a/src/main/resources/regression/msmarco-passage-cos-dpr-distil-lexlsh.yaml +++ b/src/main/resources/regression/msmarco-passage-cos-dpr-distil-lexlsh.yaml @@ -57,7 +57,7 @@ models: - name: cos-dpr-distil-lexlsh-600 display: cosDPR-distill type: inverted-dense - params: -topicfield vector -encoding lexlsh -lexlsh.b 600 -hits 1000 + params: -topicField vector -encoding lexlsh -lexlsh.b 600 -hits 1000 results: AP@1000: - 0.3509 diff --git a/src/main/resources/regression/msmarco-passage-openai-ada2.yaml b/src/main/resources/regression/msmarco-passage-openai-ada2.yaml index 20ff6f3899..16d1cd8b5a 100644 --- a/src/main/resources/regression/msmarco-passage-openai-ada2.yaml +++ b/src/main/resources/regression/msmarco-passage-openai-ada2.yaml @@ -8,7 +8,7 @@ download_checksum: a4d843d522ff3a3af7edbee789a63402 index_path: indexes/lucene-hnsw.msmarco-passage-openai-ada2/ index_type: hnsw collection_class: JsonDenseVectorCollection -generator_class: LuceneDenseVectorDocumentGenerator +generator_class: HnswDenseVectorDocumentGenerator index_threads: 16 index_options: -M 16 -efC 100 -memorybuffer 65536 @@ -53,7 +53,7 @@ models: - name: openai-ada2 display: OpenAI-ada2 type: hnsw - params: -querygenerator VectorQueryGenerator -topicfield vector -threads 16 -hits 1000 -efSearch 1000 + params: -generator VectorQueryGenerator -topicField vector -threads 16 -hits 1000 -efSearch 1000 results: AP@1000: - 0.350 diff --git a/src/test/java/io/anserini/analysis/AutoCompositeAnalyzerTest.java b/src/test/java/io/anserini/analysis/AutoCompositeAnalyzerTest.java index d52ceaefad..6ea99cfc99 100644 --- a/src/test/java/io/anserini/analysis/AutoCompositeAnalyzerTest.java +++ b/src/test/java/io/anserini/analysis/AutoCompositeAnalyzerTest.java @@ -17,9 +17,12 @@ package io.anserini.analysis; import junit.framework.JUnit4TestAdapter; +import org.apache.logging.log4j.Level; +import org.apache.logging.log4j.core.config.Configurator; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.tokenattributes.CharTermAttribute; +import org.junit.BeforeClass; import org.junit.Test; import java.io.IOException; @@ -32,6 +35,11 @@ import static org.junit.Assert.assertEquals; public class AutoCompositeAnalyzerTest { + @BeforeClass + public static void setupClass() { + Configurator.setLevel(AutoCompositeAnalyzer.class.getName(), Level.ERROR); + } + private static final Map examples = new HashMap<>() { { // Case (1): Both Lucene analyzer & monolingual tokenizer exist @@ -69,7 +77,6 @@ public void case1() throws Exception { for (int i = 0; i < example.length; i++) { List tokens = parseKeywords(analyzer, (String) example[i][0]); - System.out.println(tokens); verify((String[]) example[i][1], tokens); } } diff --git a/src/test/java/io/anserini/analysis/CompositeAnalyzerTest.java b/src/test/java/io/anserini/analysis/CompositeAnalyzerTest.java index 28ea85d934..42d0bb54a1 100644 --- a/src/test/java/io/anserini/analysis/CompositeAnalyzerTest.java +++ b/src/test/java/io/anserini/analysis/CompositeAnalyzerTest.java @@ -75,8 +75,6 @@ public List parseKeywords(Analyzer analyzer, String keywords) throws IOE tokenStream.end(); tokenStream.close(); - System.out.println(list); - return list; } diff --git a/src/test/java/io/anserini/collection/EpidemicQACollectionTest.java b/src/test/java/io/anserini/collection/EpidemicQACollectionTest.java index bac23c82aa..bbd3e84c97 100644 --- a/src/test/java/io/anserini/collection/EpidemicQACollectionTest.java +++ b/src/test/java/io/anserini/collection/EpidemicQACollectionTest.java @@ -26,6 +26,7 @@ import java.util.Map; public class EpidemicQACollectionTest extends DocumentCollectionTest { + @Before public void setUp() throws Exception { super.setUp(); diff --git a/src/test/java/io/anserini/doc/DataModel.java b/src/test/java/io/anserini/doc/DataModel.java index c51dffe4d2..299693ea32 100755 --- a/src/test/java/io/anserini/doc/DataModel.java +++ b/src/test/java/io/anserini/doc/DataModel.java @@ -288,8 +288,8 @@ public String generateIndexingCommand(String collection) { builder.append(indexCommand).append(" \\\n"); builder.append(" -collection ").append(getCollection_class()).append(" \\\n"); builder.append(" -input ").append("/path/to/"+collection).append(" \\\n"); - builder.append(" -index ").append(getIndex_path()).append(" \\\n"); builder.append(" -generator ").append(getGenerator_class()).append(" \\\n"); + builder.append(" -index ").append(getIndex_path()).append(" \\\n"); builder.append(" -threads ").append(getIndex_threads()); builder.append(" ").append(getIndex_options()).append(" \\\n"); builder.append(String.format(" >& logs/log.%s &", collection)); @@ -325,7 +325,7 @@ public String generateRankingCommand(String collection) { builder.append(searchCommand).append(" \\\n"); builder.append(" -index").append(" ").append(getIndex_path()).append(" \\\n"); builder.append(" -topics").append(" ").append(Paths.get("tools/topics-and-qrels", topic.getPath())).append(" \\\n"); - builder.append(" -topicreader").append(" ").append((topic.getTopic_reader() == null) ? getTopic_reader() : topic.getTopic_reader()).append(" \\\n"); + builder.append(" -topicReader").append(" ").append((topic.getTopic_reader() == null) ? getTopic_reader() : topic.getTopic_reader()).append(" \\\n"); builder.append(" -output").append(" ").append(generateRunFile(collection, model, topic)).append(" \\\n"); if (model.getParams() != null) { builder.append(" ").append(model.getParams()); diff --git a/src/test/java/io/anserini/index/BasicIndexOperationsTest.java b/src/test/java/io/anserini/index/BasicIndexOperationsTest.java index a6ac6ba813..7590f8a48b 100644 --- a/src/test/java/io/anserini/index/BasicIndexOperationsTest.java +++ b/src/test/java/io/anserini/index/BasicIndexOperationsTest.java @@ -45,13 +45,24 @@ import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.BytesRef; import org.apache.lucene.util.SmallFloat; +import org.junit.AfterClass; +import org.junit.BeforeClass; import org.junit.Test; +import java.io.ByteArrayOutputStream; import java.io.IOException; +import java.io.PrintStream; import java.util.HashMap; import java.util.Map; public class BasicIndexOperationsTest extends IndexerTestBase { + private final static PrintStream standardOut = System.out; + private final static ByteArrayOutputStream output = new ByteArrayOutputStream(); + + @BeforeClass + public static void setupClass() { + System.setOut(new PrintStream(output)); + } // A very simple example of how to iterate through terms in an index and dump out postings. private void dumpPostings(IndexReader reader) throws IOException { @@ -273,4 +284,9 @@ public void testIterateThroughDocumentVectorComputeBM25() throws Exception { } } } + + @AfterClass + public static void teardownClass() { + System.setOut(standardOut); + } } diff --git a/src/test/java/io/anserini/index/CloneIndexTest.java b/src/test/java/io/anserini/index/CloneIndexTest.java index 9997dee19d..70b6617bf4 100644 --- a/src/test/java/io/anserini/index/CloneIndexTest.java +++ b/src/test/java/io/anserini/index/CloneIndexTest.java @@ -31,16 +31,28 @@ import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import org.junit.After; +import org.junit.AfterClass; import org.junit.Before; +import org.junit.BeforeClass; import org.junit.Test; +import java.io.ByteArrayOutputStream; import java.io.IOException; +import java.io.PrintStream; import java.nio.file.Path; import java.util.Iterator; public class CloneIndexTest extends IndexerTestBase { + private final static PrintStream standardOut = System.out; + private final static ByteArrayOutputStream output = new ByteArrayOutputStream(); + private static Path tempDir2; + @BeforeClass + public static void setupClass() { + System.setOut(new PrintStream(output)); + } + @Before @Override public void setUp() throws Exception { @@ -153,6 +165,10 @@ public Terms terms(String s) throws IOException { public int size() { return fieldsProducer.size(); } + } + @AfterClass + public static void teardownClass() { + System.setOut(standardOut); } } diff --git a/src/test/java/io/anserini/index/IndexHnswDenseVectorsTest.java b/src/test/java/io/anserini/index/IndexHnswDenseVectorsTest.java index 6aa6be8f3c..68600ebe9c 100644 --- a/src/test/java/io/anserini/index/IndexHnswDenseVectorsTest.java +++ b/src/test/java/io/anserini/index/IndexHnswDenseVectorsTest.java @@ -16,63 +16,44 @@ package io.anserini.index; -import io.anserini.CustomAppender; import org.apache.logging.log4j.Level; -import org.apache.logging.log4j.LogManager; -import org.apache.logging.log4j.Logger; import org.apache.logging.log4j.core.config.Configurator; -import org.junit.AfterClass; +import org.apache.lucene.index.IndexReader; import org.junit.BeforeClass; import org.junit.Test; -import java.util.LinkedList; -import java.util.List; +import java.util.Map; -import static org.junit.Assert.assertTrue; +import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertNotNull; /** * Tests for {@link IndexHnswDenseVectors} */ public class IndexHnswDenseVectorsTest { - private static final Logger LOGGER = LogManager.getLogger(IndexHnswDenseVectors.class); - private static CustomAppender APPENDER; - @BeforeClass public static void setupClass() { - APPENDER = new CustomAppender("CustomAppender"); - APPENDER.start(); - - ((org.apache.logging.log4j.core.Logger) LOGGER).addAppender(APPENDER); - - Configurator.setLevel(IndexHnswDenseVectors.class.getName(), Level.INFO); + Configurator.setLevel(IndexHnswDenseVectors.class.getName(), Level.ERROR); } @Test public void test1() throws Exception { - List args = new LinkedList<>(); - args.add("-collection"); - args.add("JsonDenseVectorCollection"); - args.add("-input"); - args.add("src/test/resources/sample_docs/openai_ada2/json_vector"); - args.add("-index"); - args.add("target/idx-sample-hnsw" + System.currentTimeMillis()); - args.add("-generator"); - args.add("LuceneDenseVectorDocumentGenerator"); - args.add("-threads"); - args.add("1"); - args.add("-M"); - args.add("16"); - args.add("-efC"); - args.add("100"); - - IndexHnswDenseVectors.main(args.toArray(new String[0])); - - System.out.println(APPENDER.getLastLog()); - assertTrue(APPENDER.getLastLog().contains("Total 100 documents indexed")); - } - - @AfterClass - public static void teardownClass() { - ((org.apache.logging.log4j.core.Logger) LOGGER).removeAppender(APPENDER); + String indexPath = "target/idx-sample-hnsw" + System.currentTimeMillis(); + String[] indexArgs = new String[] { + "-collection", "JsonDenseVectorCollection", + "-input", "src/test/resources/sample_docs/openai_ada2/json_vector", + "-index", indexPath, + "-generator", "HnswDenseVectorDocumentGenerator", + "-threads", "1", + "-M", "16", "-efC", "100" + }; + + IndexHnswDenseVectors.main(indexArgs); + + IndexReader reader = IndexReaderUtils.getReader(indexPath); + assertNotNull(reader); + + Map results = IndexReaderUtils.getIndexStats(reader, Constants.VECTOR); + assertEquals(100, results.get("documents")); } } \ No newline at end of file diff --git a/src/test/java/io/anserini/index/IndexInvertedDenseVectorsTest.java b/src/test/java/io/anserini/index/IndexInvertedDenseVectorsTest.java index 7d51c16044..23e02738a9 100644 --- a/src/test/java/io/anserini/index/IndexInvertedDenseVectorsTest.java +++ b/src/test/java/io/anserini/index/IndexInvertedDenseVectorsTest.java @@ -16,32 +16,24 @@ package io.anserini.index; -import io.anserini.CustomAppender; import org.apache.logging.log4j.Level; -import org.apache.logging.log4j.LogManager; -import org.apache.logging.log4j.Logger; import org.apache.logging.log4j.core.config.Configurator; import org.apache.lucene.index.IndexReader; -import org.junit.AfterClass; import org.junit.BeforeClass; import org.junit.Test; import java.io.ByteArrayOutputStream; import java.io.PrintStream; -import java.util.LinkedList; -import java.util.List; import java.util.Map; import static org.junit.Assert.assertEquals; +import static org.junit.Assert.assertNotNull; import static org.junit.Assert.assertTrue; /** * Tests for {@link IndexInvertedDenseVectors} */ public class IndexInvertedDenseVectorsTest { - private static final Logger LOGGER = LogManager.getLogger(IndexInvertedDenseVectors.class); - private static CustomAppender APPENDER; - private final ByteArrayOutputStream err = new ByteArrayOutputStream(); private PrintStream save; @@ -57,12 +49,7 @@ private void restoreStderr() { @BeforeClass public static void setupClass() { - APPENDER = new CustomAppender("CustomAppender"); - APPENDER.start(); - - ((org.apache.logging.log4j.core.Logger) LOGGER).addAppender(APPENDER); - - Configurator.setLevel(IndexInvertedDenseVectors.class.getName(), Level.INFO); + Configurator.setLevel(IndexInvertedDenseVectors.class.getName(), Level.ERROR); } @Test @@ -141,11 +128,11 @@ public void testLLCollection() throws Exception { }; IndexInvertedDenseVectors.main(indexArgs); - assertTrue(APPENDER.getLastLog().contains("Total 100 documents indexed")); IndexReader reader = IndexReaderUtils.getReader(indexPath); - Map results = IndexReaderUtils.getIndexStats(reader, IndexInvertedDenseVectors.FIELD_VECTOR); + assertNotNull(reader); + Map results = IndexReaderUtils.getIndexStats(reader, Constants.VECTOR); assertEquals(100, results.get("documents")); assertEquals(100, results.get("non_empty_documents")); assertEquals(4081, (int) ((Long) results.get("unique_terms")).longValue()); @@ -164,19 +151,14 @@ public void testFWCollection() throws Exception { }; IndexInvertedDenseVectors.main(indexArgs); - assertTrue(APPENDER.getLastLog().contains("Total 100 documents indexed")); IndexReader reader = IndexReaderUtils.getReader(indexPath); - Map results = IndexReaderUtils.getIndexStats(reader, IndexInvertedDenseVectors.FIELD_VECTOR); + assertNotNull(reader); + Map results = IndexReaderUtils.getIndexStats(reader, Constants.VECTOR); assertEquals(100, results.get("documents")); assertEquals(100, results.get("non_empty_documents")); assertEquals(1460, (int) ((Long) results.get("unique_terms")).longValue()); assertEquals(53817, (int) ((Long) results.get("total_terms")).longValue()); } - - @AfterClass - public static void teardownClass() { - ((org.apache.logging.log4j.core.Logger) LOGGER).removeAppender(APPENDER); - } } \ No newline at end of file diff --git a/src/test/java/io/anserini/index/SimpleIndexerTest.java b/src/test/java/io/anserini/index/SimpleIndexerTest.java index b34bad66b2..6cdac44d80 100644 --- a/src/test/java/io/anserini/index/SimpleIndexerTest.java +++ b/src/test/java/io/anserini/index/SimpleIndexerTest.java @@ -21,7 +21,10 @@ import io.anserini.collection.FileSegment; import io.anserini.collection.JsonCollection; import io.anserini.search.SimpleSearcher; +import org.apache.logging.log4j.Level; +import org.apache.logging.log4j.core.config.Configurator; import org.apache.lucene.tests.util.LuceneTestCase; +import org.junit.BeforeClass; import org.junit.Test; import java.nio.file.Path; @@ -30,6 +33,10 @@ import java.util.List; public class SimpleIndexerTest extends LuceneTestCase { + @BeforeClass + public static void setupClass() { + Configurator.setLevel(SimpleIndexer.class.getName(), Level.ERROR); + } @Test public void testJsonDoc() throws Exception { diff --git a/src/test/java/io/anserini/integration/EndToEndTest.java b/src/test/java/io/anserini/integration/EndToEndTest.java index 8d49165625..65e3da2631 100644 --- a/src/test/java/io/anserini/integration/EndToEndTest.java +++ b/src/test/java/io/anserini/integration/EndToEndTest.java @@ -285,7 +285,7 @@ protected SearchCollection.Args createDefaultSearchArgs() { searchArgs.bm25 = true; // optional - searchArgs.topicfield = "title"; + searchArgs.topicField = "title"; searchArgs.searchtweets = false; searchArgs.hits = 1000; searchArgs.keepstop = false; diff --git a/src/test/java/io/anserini/integration/TweetEndToEndTest.java b/src/test/java/io/anserini/integration/TweetEndToEndTest.java index ebcb5b27c9..cfcd30f750 100644 --- a/src/test/java/io/anserini/integration/TweetEndToEndTest.java +++ b/src/test/java/io/anserini/integration/TweetEndToEndTest.java @@ -19,10 +19,18 @@ import io.anserini.collection.TweetCollection; import io.anserini.index.IndexCollection; import io.anserini.index.generator.TweetGenerator; +import org.apache.logging.log4j.Level; +import org.apache.logging.log4j.core.config.Configurator; +import org.junit.BeforeClass; import java.util.Map; public class TweetEndToEndTest extends EndToEndTest { + @BeforeClass + public static void setupClass() { + Configurator.setLevel(IndexCollection.class.getName(), Level.ERROR); + } + // Note that in the test cases, we have: // {... "id":1,"id_str":"1","text":"RT This is a Retweet and will NOT NOT be indexed!" ... } // {... "id":10,"id_str":"10","text":"This tweet won't be indexed since the maxId is 9" ... } diff --git a/src/test/java/io/anserini/search/SearchCollectionTest.java b/src/test/java/io/anserini/search/SearchCollectionTest.java index d3ba002b7d..44f68247b8 100644 --- a/src/test/java/io/anserini/search/SearchCollectionTest.java +++ b/src/test/java/io/anserini/search/SearchCollectionTest.java @@ -56,10 +56,10 @@ public void testIncompleteOptions() throws Exception { err.reset(); SearchCollection.main(new String[] {"-index", "foo", "-output", "bar"}); - assertTrue(err.toString().contains("Option \"-topicreader\" is required")); + assertTrue(err.toString().contains("Option \"-topicReader\" is required")); err.reset(); - SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicreader", "baz"}); + SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicReader", "baz"}); assertTrue(err.toString().contains("Option \"-topics\" is required")); restoreStderr(); @@ -70,7 +70,7 @@ public void testOptionErrors() throws Exception { redirectStderr(); err.reset(); - SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicreader", "baz", "-topics", "topic",}); + SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicReader", "baz", "-topics", "topic",}); assertTrue(err.toString().contains("Index path 'foo' does not exist or is not a directory.")); restoreStderr(); @@ -83,27 +83,27 @@ public void testMutallyExclusive() throws Exception { // We can't exhaustively test all combinations, so we just sample a few combinations. err.reset(); - SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicreader", "baz", "-topics", "topic", + SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicReader", "baz", "-topics", "topic", "-bm25", "-qld"}); assertTrue(err.toString().contains("cannot be used with the option")); err.reset(); - SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicreader", "baz", "-topics", "topic", + SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicReader", "baz", "-topics", "topic", "-bm25", "-qljm"}); assertTrue(err.toString().contains("cannot be used with the option")); err.reset(); - SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicreader", "baz", "-topics", "topic", + SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicReader", "baz", "-topics", "topic", "-qljm", "-spl"}); assertTrue(err.toString().contains("cannot be used with the option")); err.reset(); - SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicreader", "baz", "-topics", "topic", + SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicReader", "baz", "-topics", "topic", "-inl2", "-f2exp"}); assertTrue(err.toString().contains("cannot be used with the option")); err.reset(); - SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicreader", "baz", "-topics", "topic", + SearchCollection.main(new String[] {"-index", "foo", "-output", "bar", "-topicReader", "baz", "-topics", "topic", "-f2log", "-f2exp"}); assertTrue(err.toString().contains("cannot be used with the option")); @@ -115,7 +115,7 @@ public void testSearchLucene9() throws Exception { SearchCollection.main( new String[] {"-index", "src/test/resources/prebuilt_indexes/lucene9-index.sample_docs_trec_collection2/", "-topics", "src/test/resources/sample_topics/Trec", - "-topicreader", "Trec", "-output", "run.test", "-bm25"}); + "-topicReader", "Trec", "-output", "run.test", "-bm25"}); check("run.test", new String[]{ "1 Q0 DOC222 1 0.343200 Anserini", "1 Q0 TREC_DOC_1 2 0.333400 Anserini", @@ -125,7 +125,7 @@ public void testSearchLucene9() throws Exception { SearchCollection.main( new String[] {"-index", "src/test/resources/prebuilt_indexes/lucene9-index.sample_docs_json_collection_tokenized/", "-topics", "src/test/resources/sample_topics/json_topics1.tsv", - "-topicreader", "TsvInt", "-output", "run.test", "-pretokenized", "-impact"}); + "-topicReader", "TsvInt", "-output", "run.test", "-pretokenized", "-impact"}); check("run.test", new String[]{ "1 Q0 2000001 1 4.000000 Anserini",}); new File("run.test").delete(); @@ -136,7 +136,7 @@ public void testSearchLucene8() throws Exception { SearchCollection.main( new String[] {"-index", "src/test/resources/prebuilt_indexes/lucene8-index.sample_docs_trec_collection2/", "-topics", "src/test/resources/sample_topics/Trec", - "-topicreader", "Trec", "-output", "run.test", "-bm25"}); + "-topicReader", "Trec", "-output", "run.test", "-bm25"}); check("run.test", new String[]{ "1 Q0 DOC222 1 0.343192 Anserini", "1 Q0 TREC_DOC_1 2 0.333445 Anserini", @@ -146,7 +146,7 @@ public void testSearchLucene8() throws Exception { SearchCollection.main( new String[] {"-index", "src/test/resources/prebuilt_indexes/lucene8-index.sample_docs_json_collection_tokenized/", "-topics", "src/test/resources/sample_topics/json_topics1.tsv", - "-topicreader", "TsvInt", "-output", "run.test", "-pretokenized", "-impact"}); + "-topicReader", "TsvInt", "-output", "run.test", "-pretokenized", "-impact"}); check("run.test", new String[]{ "1 Q0 2000001 1 4.000000 Anserini",}); new File("run.test").delete(); diff --git a/src/test/java/io/anserini/search/SearchHnswDenseVectorsTest.java b/src/test/java/io/anserini/search/SearchHnswDenseVectorsTest.java new file mode 100644 index 0000000000..0ed7c91acc --- /dev/null +++ b/src/test/java/io/anserini/search/SearchHnswDenseVectorsTest.java @@ -0,0 +1,97 @@ +/* + * Anserini: A Lucene toolkit for reproducible information retrieval research + * + * Licensed under the Apache License, Version 2.0 (the "License"); + * you may not use this file except in compliance with the License. + * You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +package io.anserini.search; + +import io.anserini.index.IndexHnswDenseVectors; +import org.apache.logging.log4j.Level; +import org.apache.logging.log4j.core.config.Configurator; +import org.junit.BeforeClass; +import org.junit.Test; + +import java.io.BufferedReader; +import java.io.File; +import java.io.FileReader; +import java.io.IOException; + +import static org.junit.Assert.assertEquals; + +/** + * Tests for {@link SearchHnswDenseVectors} + */ +public class SearchHnswDenseVectorsTest { + @BeforeClass + public static void setupClass() { + Configurator.setLevel(IndexHnswDenseVectors.class.getName(), Level.ERROR); + Configurator.setLevel(SearchHnswDenseVectors.class.getName(), Level.ERROR); + } + + @Test + public void test1() throws Exception { + String indexPath = "target/idx-sample-hnsw" + System.currentTimeMillis(); + String[] indexArgs = new String[] { + "-collection", "JsonDenseVectorCollection", + "-input", "src/test/resources/sample_docs/openai_ada2/json_vector", + "-index", indexPath, + "-generator", "HnswDenseVectorDocumentGenerator", + "-threads", "1", + "-M", "16", "-efC", "100" + }; + + IndexHnswDenseVectors.main(indexArgs); + + String runfile = "target/run-" + System.currentTimeMillis(); + String[] searchArgs = new String[] { + "-index", indexPath, + "-topics", "src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-openai-ada2.jsonl", + "-output", runfile, + "-generator", "VectorQueryGenerator", + "-topicReader", "JsonIntVector", + "-topicField", "vector", + "-efSearch", "1000", + "-hits", "5"}; + SearchHnswDenseVectors.main(searchArgs); + + check(runfile, new String[] { + "160885 Q0 45 1 0.863064 Anserini", + "160885 Q0 44 2 0.861596 Anserini", + "160885 Q0 40 3 0.858651 Anserini", + "160885 Q0 48 4 0.858514 Anserini", + "160885 Q0 41 5 0.856264 Anserini", + "867490 Q0 10 1 0.850332 Anserini", + "867490 Q0 45 2 0.846281 Anserini", + "867490 Q0 44 3 0.845236 Anserini", + "867490 Q0 95 4 0.845013 Anserini", + "867490 Q0 97 5 0.844905 Anserini" + }); + + new File(runfile).delete(); + } + + protected void check(String output, String[] ref) throws IOException { + BufferedReader br = new BufferedReader(new FileReader(output)); + + int cnt = 0; + String s; + while ((s = br.readLine()) != null) { + assertEquals(ref[cnt], s); + cnt++; + } + + assertEquals(cnt, ref.length); + } + +} \ No newline at end of file diff --git a/src/test/java/io/anserini/search/SearchInvertedDenseVectorsTest.java b/src/test/java/io/anserini/search/SearchInvertedDenseVectorsTest.java index 6a41a9451c..3c6051e7b5 100644 --- a/src/test/java/io/anserini/search/SearchInvertedDenseVectorsTest.java +++ b/src/test/java/io/anserini/search/SearchInvertedDenseVectorsTest.java @@ -17,16 +17,15 @@ package io.anserini.search; import io.anserini.index.IndexInvertedDenseVectors; -import io.anserini.index.IndexInvertedDenseVectorsTest; -import io.anserini.search.SearchInvertedDenseVectors; +import org.apache.logging.log4j.Level; +import org.apache.logging.log4j.core.config.Configurator; +import org.junit.BeforeClass; import org.junit.Test; import java.io.BufferedReader; import java.io.File; import java.io.FileReader; import java.io.IOException; -import java.util.LinkedList; -import java.util.List; import static org.junit.Assert.assertEquals; @@ -34,6 +33,11 @@ * Tests for {@link SearchInvertedDenseVectors} */ public class SearchInvertedDenseVectorsTest { + @BeforeClass + public static void setupClass() { + Configurator.setLevel(IndexInvertedDenseVectors.class.getName(), Level.ERROR); + Configurator.setLevel(SearchInvertedDenseVectors.class.getName(), Level.ERROR); + } @Test public void searchFWTest() throws Exception { @@ -50,25 +54,25 @@ public void searchFWTest() throws Exception { String runfile = "target/run-" + System.currentTimeMillis(); String[] searchArgs = new String[] { "-index", indexPath, - "-topics", "src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-cos-dpr-distil.jsonl", + "-topics", "src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-openai-ada2.jsonl", "-output", runfile, - "-topicreader", "JsonIntVector", - "-topicfield", "vector", + "-topicReader", "JsonIntVector", + "-topicField", "vector", "-hits", "5", "-encoding", "fw"}; SearchInvertedDenseVectors.main(searchArgs); check(runfile, new String[] { - "2 Q0 26 1 21.478451 Anserini", - "2 Q0 122 2 19.947021 Anserini", - "2 Q0 71 3 19.537197 Anserini", - "2 Q0 80 4 19.263186 Anserini", - "2 Q0 74 5 19.188883 Anserini", - "1048585 Q0 30 1 21.119457 Anserini", - "1048585 Q0 114 2 20.725464 Anserini", - "1048585 Q0 36 3 20.413668 Anserini", - "1048585 Q0 4 4 20.092403 Anserini", - "1048585 Q0 13 5 20.087444 Anserini" + "160885 Q0 40 1 32.355999 Anserini", + "160885 Q0 44 2 31.581369 Anserini", + "160885 Q0 48 3 30.734432 Anserini", + "160885 Q0 43 4 30.215816 Anserini", + "160885 Q0 41 5 30.153873 Anserini", + "867490 Q0 97 1 33.122585 Anserini", + "867490 Q0 95 2 32.564468 Anserini", + "867490 Q0 43 3 31.937614 Anserini", + "867490 Q0 10 4 31.408100 Anserini", + "867490 Q0 45 5 30.429819 Anserini", }); new File(runfile).delete(); @@ -89,25 +93,25 @@ public void searchLLTest() throws Exception { String runfile = "target/run-" + System.currentTimeMillis(); String[] searchArgs = new String[] { "-index", indexPath, - "-topics", "src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-cos-dpr-distil.jsonl", + "-topics", "src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-openai-ada2.jsonl", "-output", runfile, - "-topicreader", "JsonIntVector", - "-topicfield", "vector", + "-topicReader", "JsonIntVector", + "-topicField", "vector", "-hits", "5", "-encoding", "lexlsh"}; SearchInvertedDenseVectors.main(searchArgs); check(runfile, new String[] { - "2 Q0 14 1 43.783421 Anserini", - "2 Q0 17 2 42.912968 Anserini", - "2 Q0 5 3 42.801838 Anserini", - "2 Q0 6 4 41.686707 Anserini", - "2 Q0 65 5 41.679508 Anserini", - "1048585 Q0 99 1 44.071457 Anserini", - "1048585 Q0 50 2 40.613106 Anserini", - "1048585 Q0 4 3 39.676960 Anserini", - "1048585 Q0 10 4 39.406578 Anserini", - "1048585 Q0 6 5 38.794933 Anserini" + "160885 Q0 97 1 82.128540 Anserini", + "160885 Q0 4 2 79.793037 Anserini", + "160885 Q0 118 3 77.931618 Anserini", + "160885 Q0 43 4 75.614052 Anserini", + "160885 Q0 65 5 74.778358 Anserini", + "867490 Q0 45 1 84.916107 Anserini", + "867490 Q0 13 2 82.500229 Anserini", + "867490 Q0 10 3 82.364830 Anserini", + "867490 Q0 44 4 79.369530 Anserini", + "867490 Q0 67 5 78.378647 Anserini", }); new File(runfile).delete(); diff --git a/src/test/java/io/anserini/search/query/PhraseQueryGeneratorTest.java b/src/test/java/io/anserini/search/query/PhraseQueryGeneratorTest.java index 5e65e999ef..dc0a128414 100644 --- a/src/test/java/io/anserini/search/query/PhraseQueryGeneratorTest.java +++ b/src/test/java/io/anserini/search/query/PhraseQueryGeneratorTest.java @@ -33,7 +33,6 @@ public void test1() { Query query = queryGenerator.buildQuery("contents", analyzer, "sample query"); assertTrue(query instanceof PhraseQuery); - System.out.println(query.toString()); assertEquals("contents:\"sampl queri\"", query.toString()); } } diff --git a/src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-openai-ada2.jsonl b/src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-openai-ada2.jsonl new file mode 100644 index 0000000000..37bcc75763 --- /dev/null +++ b/src/test/resources/sample_topics/sample-topics.msmarco-passage-dev-openai-ada2.jsonl @@ -0,0 +1,2 @@ +{"qid": 160885, "vector": [-0.002775123, 0.023983644, -0.016592458, -0.055399615, -0.009640082, 0.009077857, -0.025464624, -0.018210566, 0.021899303, 0.01212895, 0.013692207, -0.0033082073, 0.0012787164, 0.008611623, -0.014535543, 0.014562968, 0.02816604, -0.0093246875, 0.014850936, -0.014110446, -0.011703854, 0.023983644, 0.04080922, -0.022324398, 0.026122838, -0.007905415, 0.0067638266, -0.017524928, -0.009969188, -0.00089047337, 0.024216762, 2.0475423e-05, -0.0050154477, -0.008563628, -0.025327496, -0.01833398, 0.006431292, -0.013555079, 0.0072197765, 0.019869812, 0.011580439, -0.003781298, -0.0059719137, 0.018155714, 0.03131998, 0.019444715, 0.0038121517, -0.0049914503, -0.045142457, -0.004562926, 0.017991161, -0.023928793, -0.0012855728, 0.009914337, -0.015961671, -0.010764529, 0.015879394, -0.030387511, -0.01808715, -0.019554418, -0.001007032, -0.0076037343, -0.011285614, -0.0031933626, -0.019184174, -0.0015058342, -0.008933874, 0.0052005704, 0.0120672425, 0.00062350277, 0.0267262, 0.0065101404, 0.010188593, -0.008837884, 0.030168107, -0.005677089, -9.395394e-05, 0.009825204, -0.0052417084, 0.005762794, 0.018512247, -0.007329479, -0.019101897, 0.01660617, 0.029701872, 0.026931891, 0.009667507, 0.014466979, -0.00537198, -0.016853001, 0.020226344, 0.012307216, 0.025697742, 0.02370939, -0.010133741, 0.02885168, -0.020377185, 0.05153261, 0.0047583333, -0.019924663, -0.01842997, 0.0057559377, -0.0009170419, -0.02302375, -0.012540334, -0.015783405, -0.023202017, 0.013129983, 0.016359342, -0.0008249092, -0.03729875, 0.034665897, -0.01442584, -0.059568297, -0.010833093, -0.0070038005, -0.041769113, 0.018608237, -0.030689193, -0.0032122177, 0.008625336, -0.017223246, 0.016661022, -0.02034976, 0.05493338, 0.0125677595, -0.02771352, -0.017278098, 0.0055982405, -0.020390898, -0.010044608, 0.025327496, -0.0018152287, -0.0022883194, 0.006554707, 0.02702788, -0.010257157, -0.010483417, -0.018717939, -0.009180703, 0.020870844, 0.03754558, -0.021035397, 0.0035687499, 0.019485854, -0.0016112512, 0.032965515, 2.7077376e-05, -0.010380572, -0.007617447, -0.02311974, -0.04752848, 0.012108381, -0.009057288, -0.010545124, 0.04341465, -0.02623254, 0.029125936, 0.015879394, -0.0051354347, -0.01679815, -0.048406098, 0.0029362482, -0.0114981625, 0.02095312, 0.03428194, 0.0064450046, -0.011319896, 0.00692838, 0.004532072, 0.010442278, 0.05438487, -0.021213664, 0.005210855, 0.030387511, 0.026712487, -0.0010721677, 0.00023783096, -0.014192723, -0.020857133, -0.035296686, 0.009125852, 0.017703194, 0.027507829, -0.02583487, 0.020857133, -0.00071177876, -0.01660617, 0.009914337, -0.020048078, 0.0077888565, -0.012574616, 0.01670216, -0.016825575, -0.5923919, -0.00014805513, 0.017566066, -0.007946554, 0.025848582, 0.030168107, 0.012800876, -0.026054274, -0.03872488, 0.030936023, 0.012176945, 0.026602786, -0.01818314, -0.0133631, 0.008961299, -0.032883238, 0.0011261617, -0.0335963, 0.035049856, -0.0013027138, -0.015865682, 0.028906532, 0.010791955, 0.028042627, 0.0050668707, 0.004562926, 0.0076448726, -0.03636628, 0.003344203, 0.0036441702, -0.028824255, 0.015495436, -0.011381604, -0.002207757, 0.043003265, 0.006417579, 0.0076928674, 0.0126363225, -0.0036338856, 0.029208213, -0.018169427, -0.014165297, 0.031731363, 0.007055223, 0.022516377, 0.033514023, 0.028220892, 0.029180788, 0.013541366, -0.03186849, 0.005862212, 0.026493084, -0.005306844, -0.00089561567, 0.0076105907, -0.009194416, 0.02253009, -0.016619883, 0.025108093, 0.013280824, -0.010627401, 0.0061227544, -0.042893562, 0.0023294578, -0.014864649, -0.016331917, -0.025780018, 0.010737103, -0.0028505432, -0.0028539714, 0.015303458, 0.014069308, -0.036942217, 0.014796085, 0.020994259, 0.04119318, -0.019101897, -0.028659701, -0.009886911, 0.015591426, -0.012951717, 0.0034881874, -0.009180703, -0.012389493, 0.0078025693, -0.011902689, -0.0045869234, -0.018224278, 0.006506712, 0.001221294, 0.01842997, 0.038560327, 0.0094275335, -0.021419356, 0.0019095041, -0.02015778, -0.020034365, -0.026685061, 0.029619595, -0.0078574205, 0.0054988232, 0.0034847592, -0.0022848912, 0.011271901, 0.004172112, -0.004381232, -0.025601752, 0.016565032, 0.02964702, -0.00844707, 0.004525216, 0.029071085, -0.008591054, 0.0071374997, 0.011717567, -0.029921276, 0.021707324, 0.012759738, 0.008337367, -0.010133741, 0.021666186, -0.0033287762, 0.028632276, -0.047747884, -0.0052588494, 0.043112967, 0.00029396763, -0.016359342, -0.0023911654, -0.017250672, 0.014466979, 0.0072883405, 0.02642452, -0.0066129863, 0.03186849, 0.017675769, 0.027754659, -0.010620545, -0.020665154, 0.00048423238, 0.0015512578, -0.004326381, -0.018909918, -0.023777952, -0.016304491, -0.025752593, -0.0036098883, 0.01353451, -0.00943439, 0.0027408411, 0.019705258, -0.01704498, -0.0044223703, 0.0029053944, 0.02642452, -0.026561648, 0.0020774854, -0.016112512, 0.013959606, -0.001768948, 0.028714553, 0.029317915, -0.009454959, -0.013253398, 0.016757011, -0.007494032, 0.027795797, 0.051258355, 0.016126225, -0.020994259, -0.0030819464, -0.03310264, 0.0068186778, 0.020390898, 0.015221181, 0.027343275, -0.011539301, 0.017771758, 0.0017723762, 0.004343522, -0.0076585854, -0.030689193, -0.010291439, 0.0056290943, 0.006698691, -0.029455043, -0.0026379952, -0.017264385, -0.028741978, 0.044923052, 0.01837512, 0.01262261, -0.004967453, 0.02401107, -0.009310975, -0.013404238, -0.001960927, 0.0335963, 0.018841354, 0.013369956, 0.0073980424, 0.002137479, 0.008289373, -0.028769404, -0.01286944, -0.019417292, 0.0069523775, -0.016825575, 0.011792988, -0.0005935061, 0.0066541247, -0.00689067, 0.024312751, 0.021474207, 0.0003087517, -0.017058693, 0.0075694523, 0.01220437, 0.03244443, 0.0051800013, -0.0045869234, -0.006314733, 0.028015202, 0.011923258, -0.028042627, 0.015111479, 0.023723103, 0.004610921, 0.020089217, 0.0076037343, 0.0021649045, 0.006455289, 0.010956508, -0.0001338067, 0.0038875719, 0.020281196, -0.001998637, -0.004583495, 0.00569423, -0.023037463, 0.016181076, 0.0031676511, 0.01615365, 0.020829707, 0.039355665, 0.002298604, 0.052821614, 0.0019523564, 0.0073089097, 0.044182565, -0.005001735, -0.008988725, -0.029866425, 0.0020432037, -0.018567098, -0.055043083, -0.0070003723, 0.029509893, 0.030469788, 0.021199951, 0.018004874, -0.0048166127, 0.008728182, -0.0022043288, 0.003268783, 0.0041686837, -0.020925695, -0.0074391807, -0.0018460824, -0.00037110198, -0.018649375, -0.012348355, 0.024189336, 0.01763463, 0.012780307, 0.015358309, -0.020665154, -0.019732684, -0.0017338091, 0.002704845, 0.014713809, -0.038834583, 0.007446037, 0.007178638, 0.0073363353, -0.040041305, -0.00463149, -0.02034976, -0.013630499, 0.03378828, -0.0007379188, 0.016016522, -0.007281484, 0.0063592996, 0.0075763087, -0.00844707, 0.013630499, -0.020144068, -0.0072197765, 0.013335674, -0.017620917, 0.002120338, -0.016510183, -0.0073431917, -0.031649087, 0.004628062, -0.00491603, -0.028015202, 0.003517327, 0.02796035, 0.012019248, 0.009763496, -0.02331172, -0.013356243, -0.015934246, 0.0069146673, -0.06061047, 0.0074186116, -0.0007494889, -0.030606916, -0.03570807, -0.020761143, -0.030853746, 0.003412767, 0.11639404, -0.020980546, 0.009160134, 0.025368635, 0.022296974, 0.012005535, -0.019225312, -0.03685994, 0.004984594, -0.020569164, -0.0099966135, 0.0133425305, -0.017799184, 0.0120672425, -0.01818314, -0.00070277974, -0.0146726705, -0.0042886706, 0.008762464, -0.0014621248, -0.033514023, -0.009468672, -0.0022694643, 0.038121518, 0.01956813, 0.01947214, 0.024916114, 0.023723103, 0.01600281, -0.016907852, -0.007994548, 0.018923631, 0.019650407, 0.01277345, 0.0076380162, -0.020240057, 0.003447049, -0.005958201, 0.024957253, -0.004360663, 0.050298464, 0.017154682, 0.008467639, -0.032225024, 0.012602041, -0.0017912313, -0.015180043, 0.0016146793, 0.0153445965, 0.002775123, 0.016715873, -0.0072403457, 0.012108381, -0.06280451, -0.0013035708, 0.002158048, -0.009242411, -0.00085490587, 0.0126706045, -0.0060027675, -0.031128, -0.024778986, 0.02139193, 0.0065478506, -0.037326176, -0.0054165465, -0.019225312, 0.012046673, -0.030606916, -0.01108678, 0.00023226014, -0.01640048, -0.0008827599, -0.00417554, 0.0114981625, 0.010510842, -0.0028951098, 0.030881172, 0.030963447, 0.033239767, 0.019060759, -0.022859197, -0.0023791667, -0.00820024, 0.0012598613, 0.015536575, -0.0030322375, -0.0031059438, -0.025080668, -0.004381232, 0.015920533, 0.04316782, 0.014453266, -0.0186768, 0.026451945, -0.0072677713, -0.005759366, 0.010455991, -0.018827641, -0.0071649253, 0.004058982, -0.016743299, 0.016729586, 0.005272562, 0.0041686837, -0.03082632, -0.013472802, 0.027919212, -0.02044575, -0.03206047, 0.014988064, -0.020815995, 0.03008583, 0.019622982, 0.0127048865, 0.036201727, 0.0035310397, -0.0068118214, -0.0030888028, -0.01368535, 0.006115898, -0.018059725, 0.012999712, 0.02697303, -0.011525588, -0.007939697, 0.007782, 0.0017080976, -0.0049263146, 0.0035276115, 0.0051628603, -0.00039017134, 0.009619513, -0.0055399616, -0.032417003, -0.0066164145, 0.009742927, 0.027535254, -0.008680187, -0.016112512, -0.008988725, 0.0045903516, 0.037161622, -0.025423486, 0.006791252, -0.020020653, 0.015317171, 0.0040864074, -0.004785759, 0.0044806497, -0.0054885386, -0.014686383, -0.00812482, 0.00025711456, -0.00973607, -0.019280164, -0.024998391, -0.010188593, 0.019143036, 0.042866137, 0.0017980877, 0.0084265005, -0.005090868, -4.2852425e-05, 0.00046194912, 0.011923258, 0.012163232, 0.0040349844, -0.022612367, -0.011669572, 0.0075008883, 0.007919128, -0.007425468, 0.018813929, 0.009400108, 0.0041515427, -0.0044943625, -0.018388832, -0.018745365, -0.016194789, 0.019581843, 0.017346662, 0.007795713, 0.017799184, -0.028933957, -0.0102503, 0.004950312, 0.00916699, 0.012554047, -0.028906532, 0.0035961755, -0.005207427, 0.025670316, -0.044895627, -0.0023397424, -0.006962662, -0.008563628, 0.013061419, -0.019554418, 0.0007709151, 0.016866714, 0.0011998679, 0.027288424, 0.0030956592, -0.0056873737, -0.007480319, -0.012307216, -0.0043949448, -0.011189625, -0.0044977902, -0.004768618, -0.010702821, -0.032855812, -0.01402817, -0.012012391, -0.027974064, -0.011875263, 0.024998391, 0.020582877, -0.01837512, -0.002737413, -0.007075792, 0.016811863, -0.01976011, 0.0073431917, 0.022941474, 0.0018940772, -0.029016234, 0.0037607288, 0.0028779688, -0.0055193924, -0.0023585975, 0.0422902, 0.013678494, -0.026026849, 0.037189048, 0.032362152, -0.013267111, -0.01723696, 0.018704226, 0.011210194, -0.0044292267, -0.0025505763, -0.016016522, -0.02365454, 0.019403579, 0.0053479825, -0.013246542, -0.018457396, -0.02327058, -0.011402173, -0.012752881, -0.039657347, 0.0347756, 0.023489986, 0.0068872417, 0.005563959, -0.023256868, -0.010620545, 0.0018443683, -0.01091537, -0.0114981625, 0.004967453, 0.016935278, -0.00495374, 0.006945521, 0.013315105, 0.019924663, 0.014686383, 0.022694644, -0.024422454, 0.012142663, 0.0031967908, -0.023791665, 0.014782372, -0.0013541366, -0.012492339, 0.009153278, -0.0057216557, -0.0017723762, 0.01753864, 0.03304779, -0.007665442, -0.012910578, -0.018827641, -0.008501921, 0.011909545, -0.015989097, -0.008282516, -0.014000745, -0.021803314, -0.011374747, 0.015111479, -0.00611247, 0.0050325887, 0.031539384, -0.017003842, -0.0010327435, -0.021350792, 0.022063857, 0.019005908, 0.020308621, -0.034693323, -0.031539384, -0.006115898, -0.032910664, 0.021460494, -0.01660617, -0.01368535, -0.027727233, -0.015646277, 0.020555452, -0.004192681, -0.043826032, 0.02632853, 0.0044909343, 0.03249928, -0.006181034, -0.021062823, 0.047336504, 0.009544092, 0.0063935816, -0.0054336875, -0.004542357, -0.00704151, -0.02129594, 0.048104417, -0.000118594086, -0.041110903, -0.03546124, -0.010435422, 0.0006427864, 0.009304118, -0.01296543, -0.0018940772, -0.021501632, -0.008234522, 0.052327953, -0.004902317, -0.010723391, 0.062036596, 0.009454959, 0.012732312, 0.026904466, -0.005108009, 0.0073569044, -0.022036431, 0.011607865, -0.03345917, 0.009523523, -0.006331874, 0.043688904, 0.02593086, -0.0071306434, -0.008529346, -0.022365537, -0.03428194, 0.025944572, -0.01842997, 0.014220148, 0.026136551, 0.006431292, 0.00745975, 0.021419356, 0.04278386, 0.010106316, -0.019197887, -0.026534222, 0.02268093, -0.011779275, 0.02780951, 0.029427618, -0.019897237, 0.011148487, 0.03151196, -0.005478254, 0.0053102723, 0.047199376, -0.03666796, -0.025437199, -0.0066575524, -0.004682913, -0.016921565, -0.016482757, 0.014055595, 0.002773409, -0.023997357, -0.016304491, -0.0040384126, -0.0014355562, -0.017182108, 0.0074186116, 0.025423486, -0.02336657, -0.017963737, 0.0010533126, 0.00876932, -0.019732684, 0.009797778, 0.022406675, 0.024148198, 0.013164265, -0.037326176, -0.010216018, 0.01239635, 0.0012787164, -0.026369669, 0.01634563, 0.005495395, -0.017908886, -0.02860485, -0.0022488951, 0.01837512, -0.020089217, -0.007377473, -0.002317459, -0.0013455661, -0.018443683, 0.027740946, -0.001768948, -0.011395317, -0.0029910991, 0.0004400944, 0.0048714634, -0.023640826, 0.00033124923, 0.009886911, 0.0018152287, 0.02302375, 0.0077271494, -0.046458885, -0.012451201, 0.0022060429, 0.0009084714, 0.019225312, -0.008419644, 0.16696675, 0.009598943, -0.022516377, 0.01679815, -0.039712198, -0.0062941643, 0.025971998, 0.0002489726, 0.016414193, 0.008385362, -0.0013918468, -0.0006946378, -0.009818347, 0.0027271283, -0.036695387, -0.012410062, -0.031731363, -0.02800149, -0.014933213, -0.011278758, -0.020486888, -0.008844741, 0.0066027017, -0.015961671, 0.010901657, 0.007329479, -0.024724135, 0.022982612, 0.022242123, -0.023243155, 0.0025728596, -0.019129323, 0.00017055265, -0.017785471, -0.024737848, -0.019581843, -0.029372767, -0.021515345, 0.024806412, 0.035186984, 0.006588989, -0.004096692, -0.03299294, -0.025121806, -0.012663748, -0.0010087461, -0.0075077447, -0.010161167, 0.012519765, 0.0006937808, -0.039355665, -0.008707613, -0.010970221, 0.008467639, 0.023339145, -0.0102503, 0.0065512788, -0.026602786, -0.0036475984, 0.02549205, 0.014069308, 0.0014072736, -0.018813929, 0.026918178, -0.009489241, 0.013555079, 0.013033994, 0.0057182275, -4.1245457e-05, -0.018155714, 0.0211451, -0.0121358065, -0.0047789025, 0.021817027, -0.0236134, -0.007919128, 0.021364504, 0.05304102, -0.00012962858, -0.018690513, -0.020980546, -0.004511503, 0.00061793195, 0.0048440383, -0.027686095, -0.0029362482, 0.020569164, -0.026369669, -0.00647243, 0.022584941, 0.009880055, -0.02084342, -0.0059821983, -0.005886209, 0.00208777, -0.0004932314, -0.002703131, 0.050353315, -0.022516377, 0.008652762, -0.015879394, 0.029482469, -0.008639049, -0.012656892, 0.004898889, -0.0036544548, -0.0026379952, 0.014864649, 0.0030528067, 0.0029396764, 0.009009293, -0.028467722, -0.0003021096, 0.0030836605, -0.0019369295, 0.01091537, 0.007596878, 0.005975342, 0.042180497, -0.0023791667, -0.0057147993, -0.0056496635, -6.6689085e-05, 0.021227377, -0.0037847261, -0.010181736, -0.03551609, 0.0075420267, 0.027987776, -0.0361743, -0.00201235, -0.0054302593, 0.008248235, -0.0035824627, -0.004734336, 0.00012073671, 0.015975384, -0.038313497, -0.010503986, 0.00042381047, 0.0094275335, 0.0009590373, 0.009633225, -0.015714841, -0.0025882865, -0.04124803, 0.033870555, 0.0011732994, -0.009804634, 0.014124159, -0.01782661, -0.030414937, -0.007761431, -0.00042038228, 0.03913626, -0.035845198, -0.018978482, -0.02687704, 0.011916402, 0.01615365, -0.02129594, 0.0053994055, 0.017154682, -0.029400192, -0.010977077, -0.021926729, -0.17190336, 0.017470077, -0.004206394, -0.024175623, 0.009845773, -0.0059650573, 0.017264385, -0.013664781, -0.025684029, 0.018800216, 0.0035104705, -0.0051834295, -0.035872623, -0.0024134486, -0.0012221511, -0.0010147454, -0.023448847, 0.0173878, 0.0013215687, 0.0013395668, 0.020911982, -0.01901962, 0.014850936, -0.031347405, -0.009064144, -0.004209822, -0.016592458, -0.014439553, -0.0137059195, 0.0025420059, -0.021213664, -0.0014792657, 0.017374087, 0.0066472683, 0.014631532, 0.00063164474, 0.00463149, -0.0031539383, -0.030716619, 0.028303169, 0.008741895, 0.032883238, -0.004076123, -0.004470365, -0.00381558, 0.038587753, 0.0052005704, -0.019088184, 0.03293809, 0.0013987031, -0.0027356988, -0.025176657, -0.015180043, 0.011381604, 0.0137059195, -0.008639049, 0.0015752551, 0.00859791, -0.00096846477, 0.0051182937, 0.012341498, -0.03823122, 0.0028248318, -0.028070051, -0.018690513, -0.007391186, -0.015138905, 0.017182108, 0.00085490587, 0.03408996, -0.027480403, -0.031484533, 0.0006363585, -0.015358309, 0.048927184, -0.008501921, 0.016318204, 0.002350027, 0.0070963614, -0.010826237, -0.004919458, 0.046349183, -0.03315749, 0.023723103, 0.022886623, 0.029016234, 0.0008201954, 0.0053856927, 0.0093384, -0.024724135, -0.012615753, -0.03057949, -0.008152246, -0.031703938, -0.00360646, 0.034857877, -0.02811119, -0.0018460824, 0.005625666, 0.008035687, 0.009770352, -0.00020633443, -0.016331917, 0.0063935816, 0.015536575, -7.102789e-05, 0.0007567738, 0.019335015, 0.03888943, 0.008405931, -0.0049743094, 0.0011064496, 0.017566066, 0.023435134, -0.018114576, 0.023174591, -0.0472268, 0.005509108, 0.005320557, -0.018388832, 0.008015118, 0.002226612, 0.0017878031, -0.011210194, -0.022242123, 0.016030235, -0.1118414, -0.010942795, 0.026355956, -0.00812482, -0.022694644, 0.010058321, 0.0152074685, 0.008193384, 0.00044780783, 0.019033333, -0.0124991955, -0.019993227, -0.005039445, 0.0089955805, 0.016921565, -0.00095132383, -0.018320268, -0.0070963614, -0.0023911654, 0.021419356, -0.011703854, -0.032828387, -0.027247285, 0.021940442, -0.017991161, 0.011607865, 0.0074528935, 0.018731652, -0.009269836, 0.015618851, -0.0013464232, -0.0105656935, -0.016633596, -0.0071854945, -0.027836936, 0.034556195, -0.025423486, 0.0002883968, 0.008933874, -0.0022368967, 0.007651729, -0.01660617, -0.01237578, -0.034227088, 0.004562926, -0.029976128, -0.019732684, -0.01886878, 0.02148792, -0.02909851, 0.0003036094, -0.013157409, -0.017223246, -0.02530007, -0.0076928674, -0.011025072, -0.04308554, 0.044539098, 0.0026208542, -0.014988064, -0.006825534, -0.032334726, -0.011203337, 0.009201272, 0.0077545745, -0.013280824, -0.016592458, -0.012012391, 8.96687e-05, -0.01311627, -0.015618851, 0.024532156, -0.021817027, -0.022900335, -0.038450625, 0.0036475984, 0.007178638, -0.004295527, -0.027891787, -0.022022719, -0.009050432, 0.0073089097, 0.0015966813, -0.016181076, 0.03082632, 0.03779241, 0.015029202, -0.0016721016, -0.0035790345, 0.013932181, 0.0038807155, 0.010771385, 0.011614721, -0.0051834295, -0.019938376, 0.014988064, 0.008762464, 0.009441246, 0.016359342, 0.03082632, -0.0033973402, -0.013260255, -0.04377118, 0.012430632, -0.038203795, -0.0070072287, 0.035817772, 0.01729181, -0.01575598, -0.0071649253, 0.010085747, -0.0060884724, -0.040836647, 0.021007972, -0.015042915, 0.0077682873, -0.00916699, -0.0012161518, -0.0054474003, 0.010072034, 0.048296396, 0.031786215, -0.017758045, 0.00032332155, 0.008611623, 0.008289373, -0.007295197, 0.022831772, 0.00031496532, 0.03027781, -0.010147454, 0.0011775846, 0.019033333, -0.017854035, -0.003534468, -0.0050840117, -0.018649375, -0.0077271494, 0.011491306, 0.008666474, 0.013376812, 0.01262261, -0.017072406, -0.020432036, 0.0049948785, -0.033623725, 0.005591384, -0.03378828, -0.010449135, 0.022735782, 0.02025377, -0.016469045, 0.0072403457, 0.013369956, -0.03255413, -0.016825575, -0.031402256, -0.0043949448, 0.011662716, -0.00943439, 0.0025642891, -0.006287308, 0.00035053282, 0.024189336, 0.0023243155, -0.015454299, 0.015632564, 0.0066781216, -0.0133631, 0.027233573, 0.011148487, -0.017524928, -0.043634053, -0.007596878, -0.0055708154, -0.0055056796, -0.00094446744, -0.009208129, -0.009969188, 0.021529058, 0.002367168, 0.011683285, 0.004645203, -0.020911982, -0.016359342, 0.0033322044, -0.01047656, 0.039986454, -0.0054713977, -0.008193384, -0.009544092, -0.0020192063, -0.02381909, 0.007014085, 0.0007824853, -0.0047446205, -0.009612656, 0.03077147, -0.008117964, -0.0031299412, 0.004192681, 0.020198919, 0.017854035, -0.013054563, 0.009002437, -0.011361035, -0.024984678, 0.020733718, -0.031484533, -0.0049743094, -0.015372022, -0.009825204, -0.00926298, 0.018594524, 0.025176657, 0.015714841, 0.0061947466, 0.0068358188, 0.016455332, -0.005176573, -0.032718685, 0.01782661, 0.017209534, -0.0015144047, 0.0070963614, -0.0070483666, 0.018690513, -0.021899303, 0.0056633763, 0.0025900006, -0.007411755, -0.018004874, -0.014631532, -0.02475156, -0.013459089, -0.029866425, -0.00321736, -0.008296229, 0.005461113, 0.022708356, -0.0025882865, 0.09044947, 0.00086133374, 0.012005535, 0.014384702, 0.0054679695, 0.021899303, 0.0040932638, 0.016071374, -0.033733428, 0.0022677502, 0.02860485, -0.0072883405, 0.034912728, -0.009345257, -0.04654116, -0.02287291, 0.007967123, 0.005793648, -0.0057319403, -0.021364504, 0.04426484, -0.019554418, 0.026410807, 0.012279791, -0.03976705, -0.0136373555, -0.0011613007, -0.017922599, -0.016482757, -0.028070051, 0.023791665, 0.019897237, -0.017072406, -0.02835802, 0.032033045, -0.014837223, 0.0022728925, 0.002264322, 0.013548222, 0.021913016, 0.009283549, 0.02909851, -0.01818314, 0.008604767, 0.020061791, 0.0014415556, -0.03823122, 0.009448103, -0.012046673]} +{"qid": 867490, "vector": [-0.014654486, 0.018682241, -0.0049157925, -0.027302528, -0.005967319, 0.003009669, -0.01820664, -0.015397615, -0.0046817074, -0.009504609, 0.015353027, 0.018607927, -0.014394392, 0.023631474, 0.016497444, -0.018682241, 0.043012258, -0.011288117, 0.0077285324, -0.030022377, -0.016319094, -0.011392154, -0.019410506, 0.0014258771, -0.008560836, 0.014476136, 0.010604438, -0.023334224, -0.025147457, -0.018043151, 0.017835075, -0.003968304, 0.00022479625, -0.032816537, -0.0031898774, 0.005502864, -0.0148031125, 0.0047411574, 0.016958185, 0.009385708, 0.021283189, -0.06670318, -0.0032214604, -0.005135015, -0.0052762097, -0.01658662, -0.01594753, -0.02877392, -0.026514811, 0.029873751, 0.0021439246, 0.007899452, -0.016794696, -0.01113206, -0.012596021, -0.012662903, -0.0044513373, -0.0014026543, -0.028372632, -0.013621539, -0.0016432421, -0.003236323, -0.0070671486, 0.033143513, -0.010292324, 0.029769713, -0.02054006, 0.03682943, 0.011317842, -0.005636627, 3.2134485e-05, -0.009913329, -0.012254183, -0.005361669, 0.0109016895, -0.030765504, -0.007186049, -0.012967586, 0.009460021, -0.023631474, 0.00227583, -0.004562807, -0.014022828, -0.004414181, 0.029442737, -0.023230186, 0.0005963603, 0.024820479, 0.006740172, -0.013428325, -0.0040983516, 0.02511773, 0.028357768, 0.004778314, -0.006524665, 0.040574796, -0.030884406, 0.022947796, 0.013866771, -0.032340936, 0.010470675, 0.016274506, -0.029308973, -0.007145177, -0.014134297, -0.0077211014, -0.013257406, 0.022070905, 0.0049157925, -0.01461733, -0.0075241723, 0.016081292, 0.0010701045, -0.024850205, 0.015248989, -0.016839283, 0.038761564, 0.00626457, -0.017820213, -0.037721183, 0.013770164, -0.009274239, 0.007316096, -0.008523679, 0.014164022, 0.024909655, -0.03944524, 0.013235112, -0.0045256503, -0.020911625, 0.031538356, 0.019469958, 0.012744647, 0.008100096, -0.00870203, 0.04970041, -0.03659163, -0.0087689115, -0.03781036, -0.01826609, 0.0267972, 0.008991851, -0.015263852, 0.007840002, -0.027926754, 0.0042544086, 0.024448914, 0.015739454, 0.002158787, 0.00841221, 0.02186283, -0.032192312, -0.013822183, -0.018578203, -0.016229918, 0.010344343, 0.022814034, 0.019499682, -0.017835075, -0.054575328, -0.03009669, 0.013131074, 0.0018996212, -0.0032344651, 0.0109462775, 0.03033449, 0.008233859, 0.014528154, -0.01177115, -0.0050904276, 0.019202432, 0.036264654, -0.026054071, 0.0054285508, 0.011302979, 0.022397881, -0.0048451954, 0.01542734, -0.03682943, 0.008724324, 0.010567282, -0.014230903, 0.04922481, 0.028803647, -0.025593333, 0.029769713, 0.034837846, -0.022278981, -0.03792926, -0.014490998, 0.030884406, 0.040039744, 0.004183811, -0.017478373, -0.522211, -0.020718412, 0.010351775, -0.0088580875, 0.037602283, 0.03055743, 0.012105557, 0.0049269395, -0.023765238, 0.023646336, -0.0028461807, 0.02917521, -0.008196703, 0.0055920393, -0.0039460105, -0.038553488, -0.015635416, -0.0011620666, 0.019247018, -0.0012252325, -0.020317122, 0.01015113, 0.0078102765, -0.0016776117, 0.021952005, 0.013636401, -0.009430296, -0.0015652137, -0.00054805697, -0.009408002, -0.03451087, 0.011451605, 0.018890318, 0.013933652, 0.046846796, -0.02337881, 0.005881859, -0.019306468, 0.028818509, 0.027763266, -0.032162584, -0.03352994, 0.022174943, 0.014751093, 0.0019116971, 0.0061976886, -0.0037193564, 0.0023036972, -0.012863548, 0.016987909, 0.009244514, 0.019053806, 0.009229652, 0.0108496705, 0.01333915, -0.016452856, 0.026529673, -0.026172973, -0.0036320386, 0.01802829, -0.016913597, 0.028565845, -0.028224006, -0.03376774, 0.011518486, -0.008798637, -0.026455361, 0.011964363, 0.0078028454, 0.0005396968, 0.027124176, 0.009534334, 0.013242543, 0.0211197, 0.024092214, 0.06361177, -0.0049269395, 0.00037899535, -0.0105004, -0.011392154, -0.0010831093, -0.0420016, -0.023453124, 0.0020528915, 0.018043151, -0.009675528, 0.010492969, 0.017612137, -0.021342639, -0.0470846, 0.008501385, 0.04524164, -0.00980186, -0.02290321, -0.006688153, 0.0069333855, -0.020450886, 0.0063500297, -0.007434997, -0.0065618213, 0.003949726, 0.02685665, 0.0060713566, 0.0028220292, -0.02238302, -0.02117915, -0.015694866, 0.030319627, 0.032192312, -0.027168764, 0.011414448, -0.04108012, -0.037958983, -0.01252914, 0.014156591, -0.022814034, 0.0075018783, 0.005618049, -0.011429311, -0.007996059, 0.02250192, -0.014743662, 0.02006446, -0.0089101065, 0.0068627885, -0.0065841153, 0.0030226735, -0.0071674706, -0.026990414, 0.00029539343, 0.00095491967, -0.03504592, -0.0068999445, -0.011042884, 0.006781044, 0.005666352, 0.012254183, -0.001922844, 0.014119434, -0.008969557, 0.015561103, -0.01716626, 0.018860592, 0.013145937, -0.015769178, -0.018934906, -0.016750108, 0.011525917, -0.014394392, 0.021595303, -0.0051758876, -0.03629438, -0.016096156, 0.03061688, -0.0012995453, -0.046490096, 0.0047225794, -0.041674625, -0.02673775, -0.0055883233, 0.03067633, 0.0018810431, -0.018102601, -0.016467718, 0.012610884, -0.039980292, 0.017909387, 0.0128263915, -0.0050272616, -0.017864801, 0.028952273, -0.020629236, 0.001571716, 0.008984419, 0.005658921, -0.014595036, 0.01972262, 0.0061865416, -0.0032288916, 0.0036506169, -0.0067476034, -0.024850205, -0.028952273, 0.014342373, 0.019261882, -0.0028313182, 0.015219264, 0.0148179745, -0.0020584648, 0.018117463, -0.023988176, 0.011243529, -0.029308973, 0.026024347, 0.03926689, -0.00783257, 0.013591814, 0.024865067, 0.01734461, -0.01948482, 0.017939113, -0.022888346, 0.018310677, 0.012521709, 0.008620286, -0.01467678, 0.020956213, -0.003485271, 0.003845688, -0.0074275658, 0.006097366, -0.0009530618, -0.012967586, 0.012737216, -0.009786997, -0.0023408537, 0.04568752, 0.011302979, 0.0065023713, 0.0015494222, 0.011964363, -0.008382485, 0.037483383, 0.0128040975, 0.009690391, 0.027153902, 0.01884573, -0.0028703324, 0.022888346, -0.0024486072, 0.025489295, 0.017017635, -0.023036972, 0.0060342005, 0.016036704, -0.010544988, -0.008568267, -0.01966317, 0.01606643, -0.029219799, 0.0059153, 0.020079322, -0.0018327397, 0.016170468, 0.013762733, -0.01978207, 0.02597976, -0.0016153748, 0.0062571387, -0.015107795, -0.015709728, -0.0030523988, -0.008924969, 0.013524932, -0.008449367, -0.021446677, -0.0088432245, 0.010433519, 0.018801142, -0.0038754132, 0.007854864, 0.017195985, 0.019648308, 0.009675528, 0.022368157, -0.0052130437, 0.02158044, -0.020198222, 0.015174677, -0.035343174, -0.005543736, -0.01374787, 0.02226412, -0.012395377, 0.016319094, 0.008308172, -0.00065720396, -0.006896229, 0.022056043, -0.036680803, 0.0006952892, -0.049046457, 0.021729067, 0.014342373, 0.010544988, -0.005822409, -0.0027477161, -9.074291e-05, -0.032311212, 0.011087472, 0.0037063516, 0.0108868275, 0.0029762283, -0.02012391, -0.016809558, 0.02192228, 0.004291565, -0.03027504, -0.015605691, -0.04084232, 0.01223932, -0.0068999445, -1.8520146e-05, -0.01624478, -0.010656457, -0.006019338, -0.02471644, -0.019529408, -0.03225176, -0.023096422, 0.0008699244, -0.01542734, -0.034421694, -0.008902675, -0.0107753575, -0.018295815, -0.016869009, -0.010693613, 0.015040914, 0.012447396, 0.0047411574, 0.0026065218, -0.009987642, -0.04322033, 0.15445174, 0.009950486, -0.025489295, 0.018711966, 0.01722571, 0.0056923614, 0.002874048, -0.010165993, 0.025221769, 0.0042655556, 0.0060416316, 0.020317122, -0.021773655, 0.015724592, 0.016601482, 0.018711966, 0.029948063, 0.004570238, 0.005822409, -0.018801142, 0.013116212, 0.009363415, 0.037156407, 0.0534755, 0.021952005, -0.03260846, -0.0017240572, 0.011020591, -0.0019079815, -0.025786545, -0.0012428818, 0.031627532, 0.027688954, 0.012328495, 0.0018466734, 0.0012865405, 4.902904e-05, -0.04390401, 0.015561103, -0.009378277, -0.014238335, 0.0052502, 0.016229918, -0.019886108, 0.0049678115, 0.0046705604, 0.009214789, 0.025533883, 0.0032809107, -0.0067996224, 0.009341121, -0.0009005784, -0.03718613, -0.022650545, 0.00054294796, -0.020629236, 0.008337897, -0.011236098, -2.049408e-05, 0.051602818, -0.020763, -0.0005016115, -0.013383738, -0.0004621328, 0.004228399, -0.0076765134, -0.03183561, -0.0074610063, -0.020867039, -0.010753064, 3.0073466e-05, -0.015709728, -0.014245766, 0.0076059164, 0.015694866, 0.0023817257, 0.001458389, 0.0077508264, 0.01670552, 0.01055985, -0.012395377, -0.03207341, -0.024701579, 0.011525917, -0.020926489, -0.020748137, -0.013153368, -0.024270564, -0.031003306, 0.01426806, 0.02783758, -0.0008406637, 0.01044095, 0.013584382, -0.040693697, 0.014282922, 0.03317324, 0.011563074, -0.018652515, -0.029903475, -0.010909121, -0.029710263, -0.016452856, 0.0059153, 0.028387494, -0.009831585, -0.0047002854, 0.0418827, 0.008077803, -0.013175662, 0.051602818, 0.0075130253, 0.021773655, -0.0070039826, 0.01658662, 0.032400385, 0.024508366, 0.021743929, -0.017552687, 0.0064466363, 0.0020175928, -0.011161785, 0.032846265, 0.024047626, -0.008166978, 0.02360175, -0.017835075, 0.019692896, -0.00378438, 0.023809826, -0.0012605311, 0.027153902, -0.014409254, -0.02284376, -0.01902408, -0.01154078, -0.032222036, 0.020153634, 0.029933201, 0.0036524748, -0.007817708, -0.011221235, 0.003048683, -0.033946093, -0.004912077, -0.008620286, -0.011823168, 0.021194015, -0.041496273, -0.0023427114, -0.028744197, 0.014966601, -0.013807321, 0.013101349, -0.0046408353, -0.011741424, -0.009237083, 0.022100631, 0.053921375, 0.014483567, 0.018994356, 0.008100096, 0.00017277729, 0.0044922093, 0.0007203698, 0.00968296, -0.0011639245, -0.0005136873, -0.016081292, 0.04396346, 0.029308973, -0.018890318, 0.03403527, 0.020837313, -0.019380782, 0.011503624, 0.014334941, -0.02337881, -0.009318827, -0.04060452, -0.013829614, -0.048570853, 0.007906883, 0.026901238, 0.004655698, -0.0029483608, 0.031924784, 0.021952005, 0.033024613, -0.044587687, 0.01844444, 0.0031824461, -0.0016125881, -0.006662144, 1.368691e-05, -0.004310143, -0.02395845, 0.030171001, -0.0070671486, -0.029739987, -0.0022944082, 0.035580974, -0.0031824461, 0.00986131, -0.016437994, 0.008248722, -0.01954427, -0.029948063, 0.024389464, -0.032162584, -0.0015169103, 0.016631208, -0.041555725, -0.024151664, 0.0035019913, -0.002004588, -0.034213617, 0.030943856, 0.0045776693, -0.0021049103, 0.00040593374, -0.010656457, -0.004982674, -0.015650278, 0.0208819, 0.017448649, -0.0014184458, -0.0044104652, 0.015063207, 0.005135015, -0.0067773284, 0.0033013467, 0.009995073, -0.022784308, -0.008211566, 0.006368608, 0.018429577, 0.0010468818, -0.020614374, 0.01878628, -0.01461733, -0.00017602848, -0.014669349, 0.009957917, -0.042685278, 0.029145485, 0.007498163, -0.0041317926, -0.00037318966, -0.0128784105, -0.026083797, -0.0128561165, -0.03932634, 0.036324102, 0.025667645, -0.006647281, 0.008166978, -0.027644366, 0.0088432245, -0.027807854, -0.009170201, 0.014045121, 0.017597275, 0.0071154516, 0.0051944656, 0.028877959, -0.02883337, 0.005320797, 0.0050012525, 0.02889282, 0.0029706548, -0.001477896, 0.025563607, -0.019217294, -0.0029687968, -0.0019971568, -0.009251945, -0.008285878, -0.012402808, 0.0059933285, 0.0356107, -0.0021866546, -0.03097358, 0.008694599, -0.016616344, -0.039118264, 0.005577177, -0.017641861, 0.015263852, -0.033589393, -0.043339234, 0.00016313985, 0.0071191676, -0.0075316033, 0.00078446465, -0.0060713566, 0.018875454, 0.007884589, 0.0067884754, -0.009772135, -0.028253732, 0.014126866, -0.029635949, 0.017077085, -0.0007259433, -0.034600046, 0.0030226735, -0.021729067, -0.0105004, -0.019960422, -0.0073532527, 0.008211566, 0.033827193, 0.011860325, 0.00047513755, -0.010255168, 0.016155606, -0.027540328, -0.030364215, 0.03335159, -0.0015828629, -0.021803379, -0.005885575, -0.0012224457, 0.0022461046, -0.010307187, 0.012432533, 0.017924251, -0.0476791, -0.0015680003, 0.0026603986, -0.014282922, -0.0132797, -0.027926754, -0.023467986, 0.018860592, -0.020436024, 0.004808039, -0.007787983, -0.001271678, 0.008196703, 0.011622524, 0.011503624, 0.011369861, -0.044855215, -0.0026381048, -0.016690658, -0.033321865, -0.015040914, -0.035462074, -0.026425635, 0.032103136, 0.03329214, -0.027302528, -0.015457065, -0.0016358108, -0.030468253, 0.023899, -0.021372365, 0.033708293, 0.012506846, 0.013911358, 0.010359206, 0.022754584, 0.004726295, 0.008828362, -0.0032511856, -0.0029112045, 0.027361978, -0.0029390717, 0.027005276, -0.0016107302, -0.007825139, 0.019930696, 0.019380782, -0.010411225, 0.023884138, -0.014424117, -0.030706054, -0.034213617, 0.0024839058, 0.01676497, 0.011555643, 0.00945259, -0.018593065, 7.361613e-05, -0.0061047976, 0.0029520765, 0.0076393574, -0.03400554, -0.017626999, 0.02621756, 2.3498524e-05, 0.011429311, -0.01391879, 0.0210008, 0.0040351856, -0.016913597, 0.0053468067, 0.007561329, -0.00031908063, 0.02024281, 0.00017579625, -0.005220475, 0.008479092, 0.013576951, -0.018711966, 0.004165233, 0.0043770247, -0.02337881, -0.00783257, 0.0030319628, -0.0076393574, 0.008627717, 0.008077803, 0.002348285, -0.0031750149, -0.021491265, 0.036086302, -0.023096422, -0.027733542, -0.030646604, -0.008278447, -0.0052130437, 0.03287599, -0.026782338, 0.034243345, -0.048808657, -0.0034964178, 0.010247737, -0.028164556, -0.007817708, -0.013316856, 0.012194732, 0.009207358, -0.018652515, 0.17704284, 0.0046371194, -0.0109462775, 0.021550715, 0.0076690824, 0.008427073, 0.032222036, 0.023869276, -0.026425635, 0.00015477966, 0.02152099, -0.018072875, -0.0002463934, -0.0044476218, 0.006885082, -0.028848235, -0.06236331, -0.029071173, -0.019930696, -0.045330815, 0.0119495, -0.0056849304, -0.008545973, -0.0063648922, 0.016571756, 0.04848168, -0.023631474, 0.0021439246, 0.02941301, -0.0235423, 0.016928459, 0.01536789, -0.0053802477, -0.005985897, 0.01391879, -0.020777863, 0.017760763, 0.0021216308, 0.0024764745, 0.00028958774, 0.0128338225, 0.0040909206, 0.019232156, -0.00017475123, -0.0014072988, 0.010344343, 0.001241024, 0.009556628, -0.005227906, 0.0065803993, -0.03834541, -0.011912344, -0.0059301625, 0.023423398, -0.021803379, 0.008033215, 0.0038902757, 0.0029279247, -0.01872683, 0.016482582, -0.02117915, 0.038018435, -0.022085767, 0.025712233, 0.006650997, 0.00013562088, -0.01304933, 0.02048061, -0.008991851, -0.0034666928, 0.0050792806, -0.03995057, 0.0017045501, -0.012402808, -0.021550715, -0.032400385, 0.01780535, 0.04818443, -0.0016255928, 0.033500217, 0.031865332, 0.013301994, 0.019217294, 0.028313182, -0.019202432, -0.017374335, -0.0045553753, 0.0149071505, -0.0053282287, -3.7620863e-05, 0.0056403424, -0.016690658, -0.016021842, -0.014669349, 0.015144952, 0.025147457, 0.0065432433, 0.010448381, -0.02465699, 0.0062905797, -0.019187568, 0.049640957, 0.006171679, -0.007951471, -0.023036972, -0.015353027, -0.0039943135, 0.018072875, 0.015531378, -0.017314885, 0.013004743, -0.01148133, -0.0045851003, -0.00058567786, 0.022115493, -0.0024281712, 0.002337138, -0.020406298, 0.01426806, -0.012982449, 0.009029007, -0.014223472, 0.019202432, -0.0018745407, 0.0107976515, 0.018251227, -0.00484148, -0.027451154, 0.025251493, -0.03754283, 0.017998563, -0.018429577, 0.018102601, -0.00072826556, -0.006977973, -0.02152099, 0.0061233756, -0.009430296, -0.008441935, 0.0039051382, 0.005688646, -0.0006325878, 0.012744647, 0.025102869, 0.0030542566, -0.013584382, 0.033589393, 0.027302528, 0.0147585245, 0.006472646, -0.0128486855, -0.02106025, 0.0049678115, 0.0030152423, 0.010388931, 0.0071080206, -0.035224274, -0.039801944, -0.021253465, -0.016542032, -0.02094135, 0.024032764, 0.025073143, -0.017894525, -0.005904153, -0.010604438, -0.1894085, 0.021223739, 0.010255168, -0.018548477, 0.02244247, -0.005261347, 0.03329214, -0.015620553, -0.0028870527, -0.007520457, -0.026916102, 0.006710447, -0.04494439, -0.008337897, 0.00397202, 0.024003038, -0.00992076, 0.005064418, 0.020658962, 0.012447396, 0.019469958, 0.003867982, -0.010708476, -0.011332704, -0.015932666, -0.0043472997, -0.010099111, 0.04830333, 0.0011128343, 0.0034555458, 0.015144952, -0.01844444, 0.01582863, 0.0002276991, 0.008605423, 0.0057146554, -0.008464229, -0.032103136, -0.021803379, -0.010047092, -0.010322049, 0.0070782956, 0.00986131, -0.0026845504, -0.024924517, 0.0046891384, 0.035729602, 0.020450886, 0.00727894, -0.014461273, -0.0061679636, -0.031003306, -0.01624478, 0.009118182, 0.016556894, -0.010589575, 0.02997779, -0.01322025, -0.0027347114, 0.0088506555, -0.024196252, -0.009408002, 0.018756554, 0.020792725, -0.0060119065, -0.040753145, -0.032281484, -0.01688387, -0.02783758, 0.02713904, -0.03769146, 0.011236098, -0.00037156406, -0.036086302, 0.04449851, 0.0022479626, -0.013948515, -0.0065803993, 0.022412743, -0.024835343, -0.002688266, 0.036799707, -0.01548679, -0.023899, -0.005963603, -0.01055985, 0.020926489, -0.009720116, 0.01624478, -0.007631926, 0.025429845, -0.03183561, -0.01189005, -0.0067364564, 0.006138238, 0.009839016, 0.030884406, 0.028684746, -0.0071897646, -0.022635683, 0.0055585983, 0.002833176, -0.027020138, 0.009697822, 0.008382485, -0.0063723237, -0.029561637, 0.012536571, 0.041436825, -0.007765689, -0.023007248, 0.0035391478, 0.022189805, 0.019232156, 0.021387227, 0.019811796, 0.0030245315, -0.00011518486, 0.035521526, -0.016616344, 0.044557963, 0.0067550344, -0.023155872, -0.011243529, 0.016512306, -0.001199223, -0.110280216, -0.026202697, 0.028045656, 0.016898734, -0.010492969, 0.03403527, -0.0055808923, 0.031984236, -0.034421694, 0.07562072, -0.019945558, -0.010715907, 0.012112988, -0.030081827, 0.0127297845, 0.007988627, -0.016987909, -0.060460903, -0.020792725, 0.031211382, -0.015144952, 0.014966601, 0.01495917, -0.008107528, 0.011964363, 0.0058967215, -0.0033589392, 0.022591095, 0.007921746, 0.009786997, -0.0044922093, -0.041526, 0.028848235, -0.014728799, -0.021015663, -0.0046594134, -0.030468253, -0.007275224, 0.035848502, -0.051632542, 0.028030792, -0.008323035, -0.011971794, 0.0021309198, -0.028224006, -0.013056762, -0.027748404, 0.015115226, 0.031360008, 0.009794429, -0.027049864, 0.0025154888, -0.038999364, 0.0022052326, 0.0054322667, -0.016140742, 0.0021847966, 0.017433785, 0.002285119, -0.038315687, -0.016437994, 0.02030226, 0.007735964, 0.020331986, 0.017389199, -0.013985671, -0.0016534601, 0.018132327, -0.018548477, -0.014312647, -0.014773387, 0.006182826, -0.04158545, 0.007598485, -0.006045347, -0.00083369686, -0.019633446, -0.005963603, -0.0020194508, -0.022591095, -0.0013970808, -0.003121138, 0.003867982, -0.022219531, 0.024523228, -0.017077085, -0.01566514, 0.0066212714, 0.019648308, -0.0088432245, -0.012915567, 0.013294562, -0.017656725, -0.013428325, 0.010582144, 0.010455812, 0.007059717, -0.016021842, -0.0061976886, 0.024003038, -0.017151397, 0.012558865, -0.053059347, 0.021818241, -0.02198173, 0.0043027117, -0.0041912426, -0.009437727, 0.019856384, 0.004042617, 0.0068925135, 0.0128040975, -0.025444707, 0.026143247, 0.027703816, 0.007297518, -0.042031325, -0.038434587, 0.036353827, -0.016259644, 0.024850205, 0.01582863, 0.0021866546, 0.0044662002, 0.0009298391, 0.0015661425, 0.03718613, -0.014602467, 0.00571094, 0.020019872, -0.024686716, -0.023854412, -0.0072492147, -0.0119495, 0.00765422, -0.0015187681, -0.011377292, -0.0015029766, -0.0078028454, 0.004559091, -0.0066770064, 0.05769647, -0.036561903, -0.036621355, 0.027466016, 0.009170201, 0.004351015, 0.015739454, -0.055377908, 0.032192312, -0.009229652, 0.002244247, 0.022947796, 0.003028247, -0.026291873, 0.005209328, -0.029873751, -0.018236363, -0.007479585, 0.014602467, -0.009608647, -0.039058816, 0.03287599, 0.040693697, 0.0029112045, 0.020317122, -0.00678476, 0.0127743725, -0.015182108, 0.0070225606, 0.032905713, -0.010745632, -0.017656725, 0.00727894, -0.017493237, 0.028937409, 0.006286864, -0.010188286, -0.016556894, 0.005751812, -0.04030727, 0.027153902, -0.01960372, 0.013599245, -0.011013159, 0.021357503, -0.0027792992, -0.0053913947, -0.003680342, -0.0043547307, 0.045211915, 0.012506846, -0.006431774, 0.027183628, -0.00606021, -0.033262417, 0.0047745984, -0.0038902757, -0.0019098393, -0.028357768, 0.06836779, 0.04958151, 0.017656725, 0.009519471, 0.00016813274, -0.01728516, -0.015211833, 0.015620553, -0.02395845, 0.0049975365, -0.021387227, -0.015234127, 0.035164822, 0.013510069, -0.0072715087, 0.028149694, -0.021833105, 0.000733839, 0.0063983332, -0.0420016, -0.0133986, -0.0044439062, -0.0066844374, -0.01461733, 0.021535853, 0.02262082, 0.036443003, 0.013502638, 0.015471928, -0.010715907, 0.012217026, -0.0024244555, 0.016036704, -0.010983434, -0.012090694, -0.022353293, -0.016482582, -0.022353293, 0.0048229015, 0.0042321146, -0.03352994, 0.09839016, -0.011674543, -0.01027003, -0.015144952, -0.009564059, 0.003658048, -0.017537823, -0.023854412, -0.016482582, -0.009943054, 0.024047626, 0.006160532, 0.011035453, 0.014505861, 0.0014834695, 0.006212551, 0.0035521525, 0.034213617, 0.00080582954, 0.0007120096, 0.023185598, 0.03055743, -0.0067698974, -0.0052873567, 0.0043993187, 0.0009056874, 0.025519019, 0.0049083615, -0.0001054313, -0.04426071, -0.015092933, 0.04437961, -0.018875454, -0.024790755, 0.020436024, -0.006045347, -0.024746167, 0.009460021, 0.00945259, 0.053564675, -0.021327777, 0.05511038, -0.00088153576, -0.023111286, -0.008999282, -0.017939113, -0.027540328, 0.00048024656, -0.023631474]}