{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001966549,0.0001346247,0.0002222421,0.00007594022,0.000219205,0.00003651193,0.0007416927,0.0001090868,0.000004951012],"category_scores_gemma":[0.00001787915,0.0001223704,0.0000872168,0.0001076419,0.00003786037,0.0004040556,0.0001232017,0.0001462767,0.000001240994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003743246,"about_ca_system_score_gemma":0.00008319526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003385919,"about_ca_topic_score_gemma":0.0002735408,"domain_scores_codex":[0.9992349,0.00003867182,0.0001051584,0.0002603003,0.000166545,0.0001943922],"domain_scores_gemma":[0.9992419,0.00005986947,0.0001916157,0.0003471682,0.0001164303,0.00004304881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004894653,0.0001664357,0.00008988433,0.005991952,0.0003273735,0.00002488727,0.1806375,0.003525178,0.06541201,0.1626232,0.000717464,0.5799946],"study_design_scores_gemma":[0.0007980209,0.00004030959,0.004634959,0.0001724075,0.0002356758,0.00001001441,0.004896921,0.9792603,0.000143539,0.009091553,0.0003164858,0.0003998045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7671513,0.009121098,0.2206987,0.0006874464,0.0005937942,0.0007838793,0.00001157305,0.000112233,0.0008400016],"genre_scores_gemma":[0.9719041,0.00002425734,0.02328993,0.00001862537,0.00008113778,0.000001086567,0.00003957201,0.000008774287,0.004632547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9757351,"threshold_uncertainty_score":0.4990119,"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."}}