{"id":"W2606337962","doi":"","title":"Generalized Probabilistic Topic and Syntax Models for Natural Language Processing","year":2012,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Syntax; Computer science; Probabilistic logic; Natural language processing; Linguistics; Artificial intelligence; Programming language; Philosophy","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":[0.004161133,0.001495163,0.001510703,0.003001155,0.0009644658,0.00347151,0.002920312,0.002180326,0.004876371],"category_scores_gemma":[0.01567277,0.001022373,0.003262698,0.003749337,0.002439195,0.007788384,0.002117093,0.003529853,0.001947873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002490516,"about_ca_system_score_gemma":0.001822864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009322238,"about_ca_topic_score_gemma":0.008239039,"domain_scores_codex":[0.9966563,0.001640769,0.0001899071,0.0007497467,0.0005794508,0.0001838971],"domain_scores_gemma":[0.9916198,0.006392973,0.0006419781,0.0006148402,0.0006043605,0.0001259054],"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":[0.00006500042,0.00006474775,0.001428742,0.0003575589,0.0002269566,0.0002335237,0.0009004673,0.2351405,0.0009586919,0.6799292,0.007325405,0.07336927],"study_design_scores_gemma":[0.00001321484,0.00001395293,0.0003175765,0.00003209765,0.00002839681,0.00007827708,0.00004705225,0.4718629,0.0001241032,0.5208896,0.006562741,0.00003000059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004021196,0.001565403,0.9891733,0.001187269,0.00009327501,0.00008147144,0.0007272334,0.0006916545,0.002459209],"genre_scores_gemma":[0.3344317,0.005848699,0.6353701,0.00121475,0.001250434,0.001672719,0.004478342,0.0009286958,0.01480466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009322238,"threshold_uncertainty_score":0.02200645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02063657553972978,"score_gpt":0.238361680551261,"score_spread":0.2177251050115312,"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."}}