{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003715558,0.001353445,0.001255672,0.002196432,0.0006279988,0.003053521,0.003442994,0.002417107,0.004534267],"category_scores_gemma":[0.01641673,0.0007977593,0.002641621,0.002253524,0.001710114,0.004695405,0.003379181,0.003308084,0.001942136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001575413,"about_ca_system_score_gemma":0.001218959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004173832,"about_ca_topic_score_gemma":0.00560596,"domain_scores_codex":[0.9968266,0.001422457,0.0002187017,0.0005622492,0.0007763481,0.0001936784],"domain_scores_gemma":[0.9935021,0.004254694,0.0004706715,0.0008949306,0.0006241382,0.0002534551],"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":[0.0001813927,0.0001016091,0.00150674,0.0002694862,0.0001852446,0.0002782455,0.0004595977,0.1529681,0.002838111,0.6932817,0.009388517,0.1385413],"study_design_scores_gemma":[0.00003426183,0.00002872049,0.0002114043,0.00002984408,0.00004362778,0.0001332746,0.00002702769,0.5999753,0.0004526685,0.3915264,0.00749618,0.00004134311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00181249,0.0003555019,0.9948315,0.0008353207,0.00007483315,0.00003885863,0.0003021453,0.0005263443,0.001222971],"genre_scores_gemma":[0.2039946,0.001926024,0.7809874,0.00126356,0.0005781467,0.0007144646,0.001692958,0.0004518624,0.008390965],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004534267,"threshold_uncertainty_score":0.01964998,"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."}}