{"id":"W2962810136","doi":"10.18653/v1/d17-1043","title":"Piecewise Latent Variables for Neural Variational Text Processing","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":29,"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; Piecewise; Computer science; Artificial intelligence; Prior probability; Latent variable model; Inference; Probabilistic latent semantic analysis; Gaussian; Natural language; Exponential family; Artificial neural network; Algorithm; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001616551,0.0008537999,0.0007614808,0.0009352811,0.0005700391,0.001296156,0.001940416,0.00141607,0.006582571],"category_scores_gemma":[0.008021561,0.0007436207,0.001032948,0.001391218,0.001398614,0.003126536,0.001929373,0.003527716,0.001287749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001921131,"about_ca_system_score_gemma":0.001173565,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005735395,"about_ca_topic_score_gemma":0.00648198,"domain_scores_codex":[0.9993314,0.0003018502,0.00003099656,0.0001466404,0.0001371114,0.00005210405],"domain_scores_gemma":[0.9975987,0.001810363,0.0001551738,0.0001910499,0.0001621189,0.00008260261],"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":[0.00005800694,0.00003027888,0.0003621439,0.000142162,0.0000524041,0.00006473019,0.0001525222,0.3907131,0.001739088,0.5589775,0.004252942,0.04345514],"study_design_scores_gemma":[0.00000381217,0.000004393743,0.00004139779,0.000007438171,0.000003517198,0.00000859048,0.00000540482,0.8344325,0.0002013412,0.1638544,0.001431363,0.0000056843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002109811,0.0003983141,0.9955689,0.0003484387,0.00003619854,0.00001863823,0.0001242142,0.0002409572,0.001154503],"genre_scores_gemma":[0.3355601,0.002110805,0.6412418,0.0006106393,0.0004561126,0.0006016195,0.001382455,0.0009858479,0.01705068],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006582571,"threshold_uncertainty_score":0.02202088,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05132773441938535,"score_gpt":0.2843952514319339,"score_spread":0.2330675170125485,"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."}}