{"id":"W2091812280","doi":"10.1145/1273496.1273577","title":"Three new graphical models for statistical language modelling","year":2007,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":582,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Probabilistic logic; Language model; Representation (politics); Word (group theory); n-gram; Binary number; Set (abstract data type); Parametric statistics; Artificial intelligence; Natural language processing; Statistical model; Sequence (biology); Theoretical computer science; Probability distribution; Mathematics; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.000403242,0.00009721056,0.0001168758,0.00007291403,0.00006026348,0.00007230977,0.0004682689,0.00006574425,0.00001384376],"category_scores_gemma":[0.00001666701,0.00008477494,0.0000514163,0.0001222234,0.00001537745,0.0002645861,0.00009820609,0.00009945596,0.000008596734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001742534,"about_ca_system_score_gemma":0.00005153599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002859802,"about_ca_topic_score_gemma":0.0001844916,"domain_scores_codex":[0.9988536,0.000005070748,0.0002204024,0.0003420206,0.0002176423,0.000361247],"domain_scores_gemma":[0.9991432,0.000225175,0.00002353363,0.0003859044,0.00003722001,0.0001849884],"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":[0.00000512189,0.00001118331,0.000008664346,0.0000040375,0.000004031152,0.000006225396,0.0002357616,0.05199453,0.00003713382,0.9051994,0.000351421,0.04214245],"study_design_scores_gemma":[0.000156562,0.00001613392,0.000006534678,0.000002574428,0.000002035813,0.000002932127,0.00001214331,0.6584375,0.0001120348,0.3410693,0.0001045143,0.00007769149],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001688268,0.00006855802,0.9950765,0.0004187248,0.0001418583,0.0001629019,0.000001777635,0.0002094754,0.002231973],"genre_scores_gemma":[0.2979631,0.000001097208,0.7015104,0.0002541679,0.0001090668,0.000002484213,0.00000147232,0.000006417992,0.0001518253],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.606443,"threshold_uncertainty_score":0.3457022,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05588757867207705,"score_gpt":0.2949680272604291,"score_spread":0.2390804485883521,"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."}}