{"id":"W1963912989","doi":"10.1145/1236181.1236183","title":"Inferential language models for information retrieval","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Asian Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Inference; Language model; Smoothing; Term (time); Natural language processing; Artificial intelligence; Query language; Machine learning; Information retrieval; Data mining","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006953811,0.001764308,0.001620971,0.003011188,0.00111008,0.003869285,0.00291649,0.002469426,0.00589927],"category_scores_gemma":[0.02315894,0.0008761336,0.002563398,0.003511856,0.002659903,0.008618252,0.002019845,0.004085399,0.002374944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002920094,"about_ca_system_score_gemma":0.001939565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005808684,"about_ca_topic_score_gemma":0.004097866,"domain_scores_codex":[0.9933481,0.003976253,0.0004087531,0.0008552286,0.001225265,0.0001863929],"domain_scores_gemma":[0.9853462,0.01209317,0.0005664745,0.001095691,0.0007728639,0.0001255548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006584168,0.00008846119,0.0004947205,0.0002984774,0.0001276117,0.000214229,0.0003868784,0.08311794,0.0004556075,0.8505383,0.005026866,0.05918516],"study_design_scores_gemma":[0.00001863184,0.00002141123,0.0000849099,0.00004503776,0.00003228945,0.00006863752,0.00003838466,0.2821247,0.0002142971,0.7090586,0.008267879,0.0000252125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00172541,0.003045057,0.9881871,0.001267668,0.0001057186,0.0001032351,0.0003564256,0.0005521297,0.004657171],"genre_scores_gemma":[0.2420161,0.008206056,0.7339955,0.001284471,0.001257128,0.001436109,0.002309513,0.0003334773,0.009161644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006953811,"threshold_uncertainty_score":0.03677571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01074942129375895,"score_gpt":0.2498861546723253,"score_spread":0.2391367333785664,"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."}}