{"id":"W3022187094","doi":"10.1609/aaai.v31i1.10983","title":"A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues","year":2017,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":702,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal; McGill University; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Samsung; Compute Canada; Samsung Advanced Institute of Technology; Canadian Institute for Advanced Research","keywords":"Computer science; Latent variable; Generative grammar; Generative model; Latent variable model; Artificial intelligence; Variable (mathematics); Artificial neural network; Encoder; Task (project management); Machine learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003595554,0.0001126959,0.0001480982,0.00003266364,0.0006183906,0.000577991,0.001176994,0.00006830913,0.000007627094],"category_scores_gemma":[0.0001412715,0.00009423242,0.00006116986,0.00002057719,0.00002744918,0.0005513821,0.0004772572,0.00009647853,0.000009684418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002201713,"about_ca_system_score_gemma":0.000102256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008627069,"about_ca_topic_score_gemma":0.00005201518,"domain_scores_codex":[0.9988582,0.00001676324,0.000210155,0.000424587,0.0001609162,0.0003293934],"domain_scores_gemma":[0.9986754,0.00006789796,0.0000783155,0.001011974,0.00007152594,0.00009488119],"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":[0.000004082646,0.00004621932,0.0002883459,0.00001775259,0.00001798295,0.000002417448,0.000803214,0.1992843,0.002607117,0.7689807,0.001008978,0.02693883],"study_design_scores_gemma":[0.0002377357,0.00001457517,0.00002595189,0.000006911134,0.000003001792,0.000002345747,0.000001348914,0.9206507,0.0003279624,0.07835956,0.0002441443,0.0001257778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00416594,0.0000179789,0.9889501,0.001519604,0.0003167327,0.0001802015,0.000002650793,0.0001371745,0.004709592],"genre_scores_gemma":[0.2977768,0.000002503065,0.6988483,0.0004695146,0.0001486688,0.00004030995,0.000001404631,0.000007032905,0.002705534],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7213664,"threshold_uncertainty_score":0.557358,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09665800747503062,"score_gpt":0.2927783749652687,"score_spread":0.1961203674902381,"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."}}