{"id":"W2734812719","doi":"10.18653/v1/w17-4308","title":"Piecewise Latent Variables for Neural Variational Text Processing","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Nuance Foundation; Canadian Institute for Advanced Research","keywords":"Latent variable; Computer science; Piecewise; Artificial intelligence; Prior probability; Latent variable model; Probabilistic latent semantic analysis; Inference; Exponential family; Gaussian; Natural language; Machine learning; Algorithm; Mathematics; Bayesian probability","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004246431,0.0002277182,0.0002574442,0.00008390387,0.0003138118,0.001169694,0.001997648,0.0002076451,0.0000224459],"category_scores_gemma":[0.0001087375,0.0002024591,0.0001161029,0.00003169159,0.00002158235,0.0004221989,0.00170693,0.0002711365,0.00000913951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006562557,"about_ca_system_score_gemma":0.0004791859,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008859649,"about_ca_topic_score_gemma":0.000007272482,"domain_scores_codex":[0.9982529,0.00002412978,0.0003245233,0.0007838827,0.000306606,0.0003080158],"domain_scores_gemma":[0.9981868,0.00007778279,0.0003155911,0.001084765,0.0002526943,0.00008242831],"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":[0.00001140699,0.0001176792,0.0004818942,0.0006044758,0.00007516151,0.00000780903,0.0008328825,0.2090979,0.0001004471,0.402631,0.002005228,0.3840341],"study_design_scores_gemma":[0.0001824309,0.000008741239,0.0004457389,0.00007065522,0.00001208145,0.000004525072,0.000001357988,0.8987831,0.0000322109,0.09901912,0.001215924,0.0002240803],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004186977,0.0001704773,0.99033,0.003032352,0.001474458,0.0004451025,0.000009223751,0.0002358449,0.003883868],"genre_scores_gemma":[0.29482,0.000005548868,0.7017461,0.0002952952,0.0005146821,0.0001408907,0.00002106373,0.00001577996,0.002440607],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6896852,"threshold_uncertainty_score":0.9998672,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06619283798847073,"score_gpt":0.2970248572585802,"score_spread":0.2308320192701095,"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."}}