Major refactoring of search code paths (#2310)

+ Improved alignment between SearchCollection and dense vector search classes.
+ Aligned ScoredDoc and ScoredDocs (was previously ScoredDocuments) as container objects for Lucene results.
+ Searchers now use ScoredDoc instead of class-specific Result objects.
+ Tweaked SearchCollection args to use proper camelCasing.
+ Consolidated BaseSearcher class for basic ranked list post-processing functionality.
+ Increased test coverage.

Author: lintool

docs/regressions/regressions-backgroundlinking18.md

@@ -47,21 +47,21 @@ target/appassembler/bin/SearchCollection \
   -topics tools/topics-and-qrels/topics.backgroundlinking18.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v2.bm25.topics.backgroundlinking18.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 &
+  -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 \
   -output runs/run.wapo.v2.bm25+rm3.topics.backgroundlinking18.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -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 \
   -output runs/run.wapo.v2.bm25+rm3+df.topics.backgroundlinking18.txt \
-  -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.dateFilter -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 ```
 
 Evaluation can be performed using `trec_eval`:

docs/regressions/regressions-backgroundlinking19.md

@@ -47,21 +47,21 @@ target/appassembler/bin/SearchCollection \
   -topics tools/topics-and-qrels/topics.backgroundlinking19.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v2.bm25.topics.backgroundlinking19.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 &
+  -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 \
   -output runs/run.wapo.v2.bm25+rm3.topics.backgroundlinking19.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -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 \
   -output runs/run.wapo.v2.bm25+rm3+df.topics.backgroundlinking19.txt \
-  -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.dateFilter -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 ```
 
 Evaluation can be performed using `trec_eval`:

docs/regressions/regressions-backgroundlinking20.md

@@ -47,21 +47,21 @@ target/appassembler/bin/SearchCollection \
   -topics tools/topics-and-qrels/topics.backgroundlinking20.txt \
   -topicReader BackgroundLinking \
   -output runs/run.wapo.v3.bm25.topics.backgroundlinking20.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -hits 100 &
+  -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 \
   -output runs/run.wapo.v3.bm25+rm3.topics.backgroundlinking20.txt \
-  -backgroundlinking -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -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 \
   -output runs/run.wapo.v3.bm25+rm3+df.topics.backgroundlinking20.txt \
-  -backgroundlinking -backgroundlinking.datefilter -backgroundlinking.k 100 -bm25 -rm3 -hits 100 &
+  -backgroundLinking -backgroundLinking.dateFilter -backgroundLinking.k 100 -bm25 -rm3 -hits 100 &
 ```
 
 Evaluation can be performed using `trec_eval`:

docs/regressions/regressions-mb11.md

@@ -56,78 +56,78 @@ target/appassembler/bin/SearchCollection \
   -topics tools/topics-and-qrels/topics.microblog2011.txt \
   -topicReader Microblog \
   -output runs/run.mb11.bm25.topics.microblog2011.txt \
-  -searchtweets -bm25 &
+  -searchTweets -bm25 &
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb11/ \
   -topics tools/topics-and-qrels/topics.microblog2012.txt \
   -topicReader Microblog \
   -output runs/run.mb11.bm25.topics.microblog2012.txt \
-  -searchtweets -bm25 &
+  -searchTweets -bm25 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb11/ \
   -topics tools/topics-and-qrels/topics.microblog2011.txt \
   -topicReader Microblog \
   -output runs/run.mb11.bm25+rm3.topics.microblog2011.txt \
-  -searchtweets -bm25 -rm3 &
+  -searchTweets -bm25 -rm3 &
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb11/ \
   -topics tools/topics-and-qrels/topics.microblog2012.txt \
   -topicReader Microblog \
   -output runs/run.mb11.bm25+rm3.topics.microblog2012.txt \
-  -searchtweets -bm25 -rm3 &
+  -searchTweets -bm25 -rm3 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb11/ \
   -topics tools/topics-and-qrels/topics.microblog2011.txt \
   -topicReader Microblog \
   -output runs/run.mb11.bm25+ax.topics.microblog2011.txt \
-  -searchtweets -bm25 -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
+  -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 \
   -output runs/run.mb11.bm25+ax.topics.microblog2012.txt \
-  -searchtweets -bm25 -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
+  -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 \
   -output runs/run.mb11.ql.topics.microblog2011.txt \
-  -searchtweets -qld &
+  -searchTweets -qld &
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb11/ \
   -topics tools/topics-and-qrels/topics.microblog2012.txt \
   -topicReader Microblog \
   -output runs/run.mb11.ql.topics.microblog2012.txt \
-  -searchtweets -qld &
+  -searchTweets -qld &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb11/ \
   -topics tools/topics-and-qrels/topics.microblog2011.txt \
   -topicReader Microblog \
   -output runs/run.mb11.ql+rm3.topics.microblog2011.txt \
-  -searchtweets -qld -rm3 &
+  -searchTweets -qld -rm3 &
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb11/ \
   -topics tools/topics-and-qrels/topics.microblog2012.txt \
   -topicReader Microblog \
   -output runs/run.mb11.ql+rm3.topics.microblog2012.txt \
-  -searchtweets -qld -rm3 &
+  -searchTweets -qld -rm3 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb11/ \
   -topics tools/topics-and-qrels/topics.microblog2011.txt \
   -topicReader Microblog \
   -output runs/run.mb11.ql+ax.topics.microblog2011.txt \
-  -searchtweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
+  -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 \
   -output runs/run.mb11.ql+ax.topics.microblog2012.txt \
-  -searchtweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
+  -searchTweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
 ```
 
 Evaluation can be performed using `trec_eval`:

docs/regressions/regressions-mb13.md

@@ -56,78 +56,78 @@ target/appassembler/bin/SearchCollection \
   -topics tools/topics-and-qrels/topics.microblog2013.txt \
   -topicReader Microblog \
   -output runs/run.mb13.bm25.topics.microblog2013.txt \
-  -searchtweets -bm25 &
+  -searchTweets -bm25 &
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb13/ \
   -topics tools/topics-and-qrels/topics.microblog2014.txt \
   -topicReader Microblog \
   -output runs/run.mb13.bm25.topics.microblog2014.txt \
-  -searchtweets -bm25 &
+  -searchTweets -bm25 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb13/ \
   -topics tools/topics-and-qrels/topics.microblog2013.txt \
   -topicReader Microblog \
   -output runs/run.mb13.bm25+rm3.topics.microblog2013.txt \
-  -searchtweets -bm25 -rm3 &
+  -searchTweets -bm25 -rm3 &
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb13/ \
   -topics tools/topics-and-qrels/topics.microblog2014.txt \
   -topicReader Microblog \
   -output runs/run.mb13.bm25+rm3.topics.microblog2014.txt \
-  -searchtweets -bm25 -rm3 &
+  -searchTweets -bm25 -rm3 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb13/ \
   -topics tools/topics-and-qrels/topics.microblog2013.txt \
   -topicReader Microblog \
   -output runs/run.mb13.bm25+ax.topics.microblog2013.txt \
-  -searchtweets -bm25 -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
+  -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 \
   -output runs/run.mb13.bm25+ax.topics.microblog2014.txt \
-  -searchtweets -bm25 -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
+  -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 \
   -output runs/run.mb13.ql.topics.microblog2013.txt \
-  -searchtweets -qld &
+  -searchTweets -qld &
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb13/ \
   -topics tools/topics-and-qrels/topics.microblog2014.txt \
   -topicReader Microblog \
   -output runs/run.mb13.ql.topics.microblog2014.txt \
-  -searchtweets -qld &
+  -searchTweets -qld &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb13/ \
   -topics tools/topics-and-qrels/topics.microblog2013.txt \
   -topicReader Microblog \
   -output runs/run.mb13.ql+rm3.topics.microblog2013.txt \
-  -searchtweets -qld -rm3 &
+  -searchTweets -qld -rm3 &
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb13/ \
   -topics tools/topics-and-qrels/topics.microblog2014.txt \
   -topicReader Microblog \
   -output runs/run.mb13.ql+rm3.topics.microblog2014.txt \
-  -searchtweets -qld -rm3 &
+  -searchTweets -qld -rm3 &
 
 target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.mb13/ \
   -topics tools/topics-and-qrels/topics.microblog2013.txt \
   -topicReader Microblog \
   -output runs/run.mb13.ql+ax.topics.microblog2013.txt \
-  -searchtweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
+  -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 \
   -output runs/run.mb13.ql+ax.topics.microblog2014.txt \
-  -searchtweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
+  -searchTweets -qld -axiom -axiom.beta 1.0 -axiom.deterministic -rerankCutoff 20 &
 ```
 
 Evaluation can be performed using `trec_eval`:

docs/regressions/regressions-msmarco-passage-ca.md

@@ -21,11 +21,11 @@ Typical indexing command:
 ```
 target/appassembler/bin/IndexCollection \
   -collection JsonCollection \
-  -input /path/to/msmarco-wp \
+  -input /path/to/msmarco-passage \
   -generator DefaultLuceneDocumentGenerator \
   -index indexes/lucene-index.msmarco-passage-ca/ \
   -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer \
-  >& logs/log.msmarco-wp &
+  >& logs/log.msmarco-passage &
 ```
 
 The directory `/path/to/msmarco-passage-wp/` should be a directory containing the corpus in Anserini's jsonl format.
@@ -44,17 +44,17 @@ target/appassembler/bin/SearchCollection \
   -index indexes/lucene-index.msmarco-passage-ca/ \
   -topics tools/topics-and-qrels/topics.msmarco-passage.dev-subset.txt \
   -topicReader TsvInt \
-  -output runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt \
-  -bm25  -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer &
+  -output runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt \
+  -bm25 -analyzeWithHuggingFaceTokenizer bert-base-uncased -useCompositeAnalyzer &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```
-tools/eval/trec_eval.9.0.4/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt
 ```
 
 ## Effectiveness

docs/regressions/regressions-msmarco-passage-hgf-wp.md

@@ -23,11 +23,11 @@ Typical indexing command:
 ```
 target/appassembler/bin/IndexCollection \
   -collection JsonCollection \
-  -input /path/to/msmarco-wp \
+  -input /path/to/msmarco-passage \
   -generator DefaultLuceneDocumentGenerator \
   -index indexes/lucene-index.msmarco-passage-hgf-wp/ \
   -threads 9 -storePositions -storeDocvectors -storeRaw -analyzeWithHuggingFaceTokenizer bert-base-uncased \
-  >& logs/log.msmarco-wp &
+  >& logs/log.msmarco-passage &
 ```
 
 The directory `/path/to/msmarco-passage-wp/` should be a directory containing the corpus in Anserini's jsonl format.
@@ -46,17 +46,17 @@ 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 \
-  -output runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt \
-  -bm25  -analyzeWithHuggingFaceTokenizer  bert-base-uncased &
+  -output runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt \
+  -bm25 -analyzeWithHuggingFaceTokenizer  bert-base-uncased &
 ```
 
 Evaluation can be performed using `trec_eval`:
 
 ```
-tools/eval/trec_eval.9.0.4/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt
-tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-wp.bm25-default.topics.msmarco-passage.dev-subset.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m map tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -M 10 -m recip_rank tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.100 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt
+tools/eval/trec_eval.9.0.4/trec_eval -c -m recall.1000 tools/topics-and-qrels/qrels.msmarco-passage.dev-subset.txt runs/run.msmarco-passage.bm25-default.topics.msmarco-passage.dev-subset.txt
 ```
 
 ## Effectiveness

src/main/java/io/anserini/rerank/Reranker.java

@@ -16,7 +16,9 @@
 
 package io.anserini.rerank;
 
+import io.anserini.search.ScoredDocs;
+
 public interface Reranker<T> {
-  ScoredDocuments rerank(ScoredDocuments docs, RerankerContext<T> context);
+  ScoredDocs rerank(ScoredDocs docs, RerankerContext<T> context);
   String tag();
 }

src/main/java/io/anserini/rerank/RerankerCascade.java

@@ -16,6 +16,8 @@
 
 package io.anserini.rerank;
 
+import io.anserini.search.ScoredDocs;
+
 import java.util.ArrayList;
 import java.util.List;
 
@@ -57,8 +59,8 @@ public RerankerCascade add(Reranker reranker) {
    * @return reranked results
    */
   @SuppressWarnings("unchecked")
-  public ScoredDocuments run(ScoredDocuments docs, RerankerContext context) {
-    ScoredDocuments results = docs;
+  public ScoredDocs run(ScoredDocs docs, RerankerContext context) {
+    ScoredDocs results = docs;
 
     for (Reranker reranker : rerankers) {
       results = reranker.rerank(results, context);