{"id":"W3103356223","doi":"10.18653/v1/2020.emnlp-main.101","title":"Learning VAE-LDA Models with Rounded Reparameterization Trick","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Artificial intelligence; Generative grammar; Benchmark (surveying); Topic model; Dirichlet distribution; Generative model; Machine learning; Mathematics","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":[0.00007928452,0.00007995617,0.00009862668,0.00002999567,0.00006654035,0.0001607459,0.0003311154,0.00002956933,0.0000110664],"category_scores_gemma":[0.00002937356,0.00006428161,0.00002193691,0.0003302053,0.000007542762,0.0006881817,0.0001145025,0.0001033956,0.00002013555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001829491,"about_ca_system_score_gemma":0.00003850255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002747205,"about_ca_topic_score_gemma":0.000001510949,"domain_scores_codex":[0.9991382,0.00003944223,0.0001372099,0.0003407062,0.0001990029,0.0001454563],"domain_scores_gemma":[0.9995657,0.00002774275,0.00005039221,0.0002314164,0.00004405161,0.00008072588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000158925,0.00001596152,0.0002636783,0.00001214429,0.00001556741,0.00001353667,0.002728152,0.8180127,0.0008936917,0.1493131,0.0001337868,0.02858182],"study_design_scores_gemma":[0.0001953979,0.0001220494,0.00001769272,0.000003921782,0.000001855749,0.000004284037,0.00003880968,0.9964882,0.0003520805,0.00197804,0.0006981983,0.00009950464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.020973,0.000009592853,0.9693004,0.00237513,0.00003637167,0.00008606783,7.040337e-8,0.0004229224,0.006796475],"genre_scores_gemma":[0.7131797,0.00000312151,0.2855583,0.0009477171,0.00002895432,0.000003667905,0.000001155166,0.000005455769,0.0002719642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6922067,"threshold_uncertainty_score":0.2621328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0449443518106457,"score_gpt":0.2241349230300437,"score_spread":0.179190571219398,"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."}}