{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002071332,0.0001162394,0.0001734402,0.00007133117,0.0001141075,0.0001782289,0.0003240945,0.00005054036,0.000001135029],"category_scores_gemma":[0.00001607997,0.00007255767,0.00003193956,0.0001264455,0.00001214387,0.002620799,0.00005287455,0.00006095138,0.00000208587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005655701,"about_ca_system_score_gemma":0.00007286629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003610772,"about_ca_topic_score_gemma":0.000002681201,"domain_scores_codex":[0.9988252,0.00002112815,0.000542978,0.000138975,0.00027557,0.0001961794],"domain_scores_gemma":[0.9991201,0.00002875273,0.0002779686,0.0002490805,0.0002760053,0.00004812392],"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":[0.0000255138,0.00005210883,0.0005026914,0.001728909,0.00002282695,8.420859e-7,0.005587927,0.1750975,0.0003776422,0.1038883,0.00003419912,0.7126817],"study_design_scores_gemma":[0.0004207514,0.00003096585,0.00001178452,0.0003187798,0.000004112581,0.00002198375,0.0001752487,0.9969612,0.0001599503,0.0006660309,0.001113214,0.0001159468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07473148,0.00002615116,0.9233799,0.0009269227,0.0002578705,0.0002591162,0.000004232719,0.0001032207,0.0003110983],"genre_scores_gemma":[0.9419568,0.000001683375,0.057539,0.0001226137,0.0001089955,0.00003377645,0.000004979277,0.000005930433,0.0002262074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8672253,"threshold_uncertainty_score":0.2958816,"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."}}