{"id":"W3096542808","doi":"10.1145/3402884","title":"Condition-Transforming Variational Autoencoder for Generating Diverse Short Text Conversations","year":2020,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Natural Science Foundation of China","keywords":"Latent variable; Autoencoder; Sequence (biology); Dependency (UML); Conditional probability distribution; Computer science; Artificial intelligence; Gaussian; Latent variable model; Pattern recognition (psychology); Transformation (genetics); Variable (mathematics); Multivariate normal distribution; Multivariate statistics; Algorithm; Mathematics; Statistics; Machine learning","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":[0.0001561765,0.0001590321,0.0001367931,0.00015351,0.0007031143,0.0004372928,0.0003167149,0.00008519393,0.00006238711],"category_scores_gemma":[0.0000722812,0.0001636325,0.00006580452,0.000266232,0.0000341721,0.002518214,0.00001328844,0.0001884801,0.00001565719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004322093,"about_ca_system_score_gemma":0.0001015819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006928672,"about_ca_topic_score_gemma":0.000004035342,"domain_scores_codex":[0.9988826,0.00002344787,0.0003848633,0.0002295852,0.00026163,0.0002178549],"domain_scores_gemma":[0.9993693,0.00008100276,0.0001012749,0.0002054061,0.0001001686,0.0001428947],"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":[0.00001864894,0.00002725042,0.00001856541,0.0002049547,0.00002963881,0.000001717399,0.07419676,0.05406592,0.0004971637,0.001859869,0.00007278075,0.8690068],"study_design_scores_gemma":[0.0005826923,0.00004050602,0.0000448192,0.00005493784,0.00002223374,0.00001233605,0.008427579,0.9872597,0.0009409731,0.0001326846,0.00227234,0.0002091814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003428221,0.00002463883,0.9905109,0.004457956,0.00006385287,0.0003359934,0.00004533732,0.0002555987,0.0008775121],"genre_scores_gemma":[0.7959271,0.000002252465,0.1998628,0.003944876,0.00008433835,0.00005713858,0.00007734136,0.000009789804,0.00003432815],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9331938,"threshold_uncertainty_score":0.6672739,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01530751449655362,"score_gpt":0.2482199830368645,"score_spread":0.2329124685403109,"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."}}