{"id":"W4391680357","doi":"10.1145/3640460","title":"Revisiting Bag of Words Document Representations for Efficient Ranking with Transformers","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Information Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Computer science; Transformer; Search engine indexing; Inference; ENCODE; Artificial intelligence; Question answering; Information retrieval; Machine learning; Natural language processing; Voltage","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001905727,0.000965622,0.0014159,0.001936211,0.0004384893,0.002566481,0.001916724,0.0008113269,0.004446006],"category_scores_gemma":[0.009744365,0.0004510947,0.0008460218,0.003203589,0.0007823349,0.006673744,0.001583647,0.001889517,0.004055053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008998,"about_ca_system_score_gemma":0.001992778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005040421,"about_ca_topic_score_gemma":0.007321677,"domain_scores_codex":[0.9985863,0.0005129353,0.0001296337,0.0002217587,0.0004187786,0.0001305564],"domain_scores_gemma":[0.9970489,0.001372321,0.00018844,0.0008292184,0.0004855883,0.00007565438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000537569,0.0002724984,0.001343596,0.000440066,0.00009212266,0.0001157127,0.0002726247,0.1495079,0.01593538,0.07433572,0.01776751,0.7393792],"study_design_scores_gemma":[0.00006751157,0.0001756521,0.0002374738,0.00002459718,0.00003275599,0.0001069995,0.00008598909,0.9165496,0.007116198,0.07019403,0.005374593,0.00003457674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02134456,0.0007523831,0.9688634,0.0004104358,0.00009733298,0.0001214823,0.0007541176,0.005766901,0.001889401],"genre_scores_gemma":[0.4349084,0.001243215,0.5524042,0.0003951453,0.0002451658,0.0002758024,0.003651007,0.0006606335,0.00621636],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005040421,"threshold_uncertainty_score":0.01487333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01808328787664678,"score_gpt":0.2747271749205496,"score_spread":0.2566438870439028,"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."}}