{"id":"W4391840390","doi":"10.1145/3648471","title":"Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges","year":2024,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Topic Modeling","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; Central China Normal University; York University","keywords":"Computer science; Information retrieval; Data science; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01091973,0.0004557237,0.001062193,0.0004007245,0.0002489754,0.0006691805,0.002035331,0.0003378636,4.159453e-7],"category_scores_gemma":[0.001117584,0.0004100026,0.0002145944,0.00068131,0.00004030071,0.0004011433,0.001880794,0.0004529591,0.00004679199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001013353,"about_ca_system_score_gemma":0.0001870657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008136657,"about_ca_topic_score_gemma":0.00002470933,"domain_scores_codex":[0.9962124,0.001136526,0.001023359,0.0008401802,0.0003469344,0.0004406233],"domain_scores_gemma":[0.9942919,0.003256066,0.0004865185,0.001638893,0.0002136263,0.0001129835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[4.363323e-7,0.000005615259,0.000005730157,0.01147224,0.00005255929,4.979148e-7,0.0002540291,0.000003438028,5.568348e-9,0.004134792,0.0001685055,0.9839022],"study_design_scores_gemma":[0.00008709168,0.00002319994,0.0001097186,0.00310575,0.0000937811,0.00002666096,0.00001364895,0.01134747,8.766757e-8,0.0009438229,0.9838248,0.0004239647],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001263161,0.6366642,0.3615709,0.00009449816,0.0003716763,0.0008308718,0.00003294273,0.0003103604,0.0001232515],"genre_scores_gemma":[0.00005724247,0.9596801,0.03963272,0.00003333696,0.0002648228,0.00005693936,0.0001937948,0.00004327732,0.0000377701],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9836563,"threshold_uncertainty_score":0.9998352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1611122394518345,"score_gpt":0.3541270262094905,"score_spread":0.1930147867576561,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}