{"id":"W2990321249","doi":"10.1111/coin.12248","title":"A topic‐based term frequency normalization framework to enhance probabilistic information retrieval","year":2019,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Yenepoya Research Centre","keywords":"Computer science; Divergence-from-randomness model; Normalization (sociology); Term Discrimination; Probabilistic logic; Artificial intelligence; Term (time); Language model; Natural language processing; Embedding; Sentence; Vector space model; Information retrieval; Visual Word","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002466689,0.0001445663,0.0001340823,0.0001715212,0.00008470641,0.0002264064,0.0007734105,0.00008192835,0.00009630279],"category_scores_gemma":[0.0003749074,0.0001513857,0.00004722063,0.0006725864,0.00002194186,0.001062346,0.0001375632,0.0001521825,0.0009697303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001297843,"about_ca_system_score_gemma":0.0002005819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001128727,"about_ca_topic_score_gemma":0.00000130113,"domain_scores_codex":[0.9984164,0.00004579233,0.0004563119,0.000347342,0.0005016762,0.0002324709],"domain_scores_gemma":[0.9985834,0.0002909573,0.0001348673,0.0004594616,0.0004285467,0.0001027055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000711848,0.00002034035,0.0009896202,0.00004448757,0.000003461241,8.858972e-7,0.0007602185,0.6919637,0.00005458376,0.283106,0.00001925919,0.02303036],"study_design_scores_gemma":[0.00003319565,0.00008226902,0.002057096,0.0001039304,0.000001993724,0.000004485928,0.00001288276,0.8669122,0.001514601,0.1288702,0.0002050163,0.0002020327],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02911799,0.00001815246,0.9679973,0.0007987516,0.000658547,0.0004779434,0.000003110292,0.0001554909,0.0007727025],"genre_scores_gemma":[0.6419575,7.645368e-7,0.3567082,0.001223519,0.00004120919,0.00001191594,0.00001593307,0.00000396909,0.00003695528],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6128395,"threshold_uncertainty_score":0.9998081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01777396872445287,"score_gpt":0.2958569037642808,"score_spread":0.2780829350398279,"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."}}