diff --git a/catalogue-1.4.json b/catalogue-1.4.json index 66a4c2c..6445160 100644 --- a/catalogue-1.4.json +++ b/catalogue-1.4.json @@ -16,6 +16,9 @@ "glf": { "path": "disambig_bert_unfactored/glf" }, + "lev": { + "path": "disambig_bert_unfactored/lev" + }, "msa": { "path": "disambig_bert_unfactored/msa" } @@ -41,6 +44,9 @@ "calima-glf-01": { "path": "disambig_ranking_cache/calima-glf-01" }, + "calima-lev-01": { + "path": "disambig_ranking_cache/calima-lev-01" + }, "calima-msa-r13": { "path": "disambig_ranking_cache/calima-msa-r13" } @@ -55,6 +61,9 @@ "calima-glf-01": { "path": "morphology_db/calima-glf-01" }, + "calima-lev-01": { + "path": "morphology_db/calima-lev-01" + }, "calima-msa-r13": { "path": "morphology_db/calima-msa-r13" } @@ -102,7 +111,8 @@ "disambig-mle-calima-msa-r13", "sentiment-analysis-arabert", "ner-arabert", - "dialectid-default" + "dialectid-default", + "disambig-bert-unfactored-msa" ], "description": "Default datasets for all CAMeL Tools components", "name": "defaults", @@ -437,7 +447,8 @@ "dependencies": [ "disambig-bert-unfactored-msa", "disambig-bert-unfactored-egy", - "disambig-bert-unfactored-glf" + "disambig-bert-unfactored-glf", + "disambig-bert-unfactored-lev" ], "description": "All available unfactored BERT disambiguation models", "name": "disambig-bert-unfactored-all", @@ -570,6 +581,69 @@ "url": "https://github.com/CAMeL-Lab/camel-tools-data/releases/download/2022.04.26/disambig_bert_unfactored-glf-1.0.1.zip", "version": "1.0.1" }, + "disambig-bert-unfactored-lev": { + "dependencies": [ + "morphology-db-lev-01", + "disambig-ranking-cache-calima-lev-01" + ], + "description": "Unfactored BERT model for disambiguating Levantine Arabic", + "destination": "disambig_bert_unfactored/lev", + "files": [ + { + "path": "LICENSE", + "sha256": "54f0cb9fb9c33cc3d46b51b01477cd7350e869b0630d72a087125ad6206b482a", + "size": 1087 + }, + { + "path": "config.json", + "sha256": "5ecd10ab10d3ad6f363468e1efde47c53833954b9622e42f9b4d3a37db178c9c", + "size": 376547 + }, + { + "path": "default_config.json", + "sha256": "ccfa0b9a9f7f1ed0187dbb6a8171338076383b67208e0eff50aa468d19a90e10", + "size": 274 + }, + { + "path": "mle_model.json", + "sha256": "2299a76a3d428d1278a2320b1b9f7636188bbba1d21b2e29fd734fab2836fa5d", + "size": 463099 + }, + { + "path": "pytorch_model.bin", + "sha256": "cf9314d41c553220fdcd4568686f3bc1d90a34f183ecb26fdbfd51150a3fe5d5", + "size": 440049614 + }, + { + "path": "special_tokens_map.json", + "sha256": "303df45a03609e4ead04bc3dc1536d0ab19b5358db685b6f3da123d05ec200e3", + "size": 112 + }, + { + "path": "tokenizer_config.json", + "sha256": "73f5e97ab29042bac49dc96f7b8a7a790994509bbd2fe3e9cd4f59affc46c2ce", + "size": 86 + }, + { + "path": "training_args.bin", + "sha256": "3e9189cce1ba41254f1600af88b07728c59fda061332a72ae21d0e1c31c215f3", + "size": 1346 + }, + { + "path": "vocab.txt", + "sha256": "1df5f8da6ad6c56153c7a974c0b149bb7a0a6e332bcfa795c99deee6c1136ce2", + "size": 304561 + } + ], + "license": "MIT", + "name": "disambig-bert-unfactored-lev", + "package_type": "http", + "private": false, + "sha256": "6383e81837d362b66c15ff1cf29dcc0d3d41c42d71e7e8591389ee1a95a41ffa", + "size": 441196726, + "url": "https://github.com/CAMeL-Lab/camel-tools-data/releases/download/2022.05.30/disambig_bert_unfactored-lev-1.0.0.zip", + "version": "1.0.0" + }, "disambig-bert-unfactored-msa": { "dependencies": [ "morphology-db-msa-r13", @@ -747,6 +821,31 @@ "url": "https://github.com/CAMeL-Lab/camel-tools-data/releases/download/2022.04.26/disambig_ranking_cache_calima-glf-01-1.0.0.zip", "version": "1.0.0" }, + "disambig-ranking-cache-calima-lev-01": { + "dependencies": [], + "description": "Disambiguation ranking cache synced with the calima-lev-01 morphology database.", + "destination": "disambig_ranking_cache/calima-lev-01", + "files": [ + { + "path": "LICENSE", + "sha256": "25fb60e0e59565106c6aa8eb6bd0492fb8cbe8211e5636bda2916de6ecdad886", + "size": 251 + }, + { + "path": "default_cache.pickle", + "sha256": "0e9249be7b367779ab5b59ee97d4997a0c25735cca35697de4789901fc91eb74", + "size": 18255108 + } + ], + "license": "CC BY 4.0", + "name": "disambig-ranking-cache-calima-lev-01", + "package_type": "http", + "private": true, + "sha256": "087c356a4be89ada37693152ab41e16403a960c36f4a3b960ac84a9d23e6d8be", + "size": 18255359, + "url": "https://github.com/CAMeL-Lab/camel-tools-data/releases/download/2022.05.30/disambig_ranking_cache_calima-lev-01-1.0.0.zip", + "version": "1.0.0" + }, "disambig-ranking-cache-calima-msa-r13": { "dependencies": [], "description": "Disambiguation ranking cache synced with the calima-msa-r13 morphology database.", @@ -776,6 +875,7 @@ "dependencies": [ "morphology-db-msa-r13", "morphology-db-glf-01", + "morphology-db-lev-01", "morphology-db-egy-r13" ], "description": "All available morphology databases", @@ -835,6 +935,33 @@ "url": "https://github.com/CAMeL-Lab/camel-tools-data/releases/download/2022.03.30/morphology_db_calima-glf-01-0.1.0.zip", "version": "0.1.0" }, + "morphology-db-lev-01": { + "dependencies": [ + "morphology-db-lev-01" + ], + "description": "Database for analyzing Levantine Arabic", + "destination": "morphology_db/calima-lev-01", + "files": [ + { + "path": "LICENSE", + "sha256": "25fb60e0e59565106c6aa8eb6bd0492fb8cbe8211e5636bda2916de6ecdad886", + "size": 251 + }, + { + "path": "morphology.db", + "sha256": "938b2f15af034cd1130afd30a142610e8602415a533aab3af403fa118210fc1f", + "size": 10621699 + } + ], + "license": "CC BY 4.0", + "name": "morphology-db-lev-01", + "package_type": "http", + "private": false, + "sha256": "34f012383f18196554ec38ec1d4e6c8d1cc767b25e00c397cd36c67afaf4c3c4", + "size": 10621950, + "url": "https://github.com/CAMeL-Lab/camel-tools-data/releases/download/2022.05.30/morphology_db_calima-lev-01-0.1.0.zip", + "version": "0.1.0" + }, "morphology-db-msa-r13": { "dependencies": [], "description": "Database for analyzing Modern Standard Arabic", @@ -1030,5 +1157,5 @@ "version": "1.0.0" } }, - "version": "1.4.2" + "version": "1.4.3" }