{"id":"W2550969563","doi":"","title":"Online Bayesian Moment Matching for Topic Modeling with Unknown Number of Topics","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Latent Dirichlet allocation; Hierarchical Dirichlet process; Hyperparameter; Topic model; Computer science; Dirichlet distribution; Matching (statistics); Dirichlet process; Bayesian probability; Moment (physics); Parametric statistics; Simple (philosophy); Machine learning; Prior probability; Artificial intelligence; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.004888,0.001065324,0.002173879,0.002083364,0.0009993812,0.001614702,0.002802236,0.002266162,0.004698823],"category_scores_gemma":[0.02057601,0.001313054,0.001600309,0.00295612,0.001380768,0.00522289,0.002574865,0.003342281,0.002330843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001641692,"about_ca_system_score_gemma":0.001843672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003513697,"about_ca_topic_score_gemma":0.004690901,"domain_scores_codex":[0.9965392,0.001570319,0.0001779117,0.0009036454,0.0005925183,0.000216267],"domain_scores_gemma":[0.9936511,0.004454697,0.0004735098,0.000830329,0.0004335278,0.0001568724],"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":[0.0005808195,0.0003179644,0.001994638,0.0004534352,0.0002309932,0.0002923669,0.0006417193,0.3554786,0.008479263,0.2023569,0.01273847,0.4164348],"study_design_scores_gemma":[0.00002813839,0.00001941703,0.0002743747,0.00001681009,0.00001729213,0.00007051937,0.0000232003,0.8843915,0.001110093,0.1114068,0.002613363,0.00002841165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003123935,0.000307716,0.9953941,0.000147339,0.00002517031,0.00003008199,0.0001136364,0.0004514712,0.0004065801],"genre_scores_gemma":[0.1946047,0.001132298,0.7952873,0.0003550984,0.0004452785,0.000649566,0.002008825,0.0006840635,0.004832927],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004888,"threshold_uncertainty_score":0.02585053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02447757697014753,"score_gpt":0.270906195122266,"score_spread":0.2464286181521185,"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."}}