{"id":"W2399880602","doi":"10.1609/aaai.v31i1.10983","title":"A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues","year":2017,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":266,"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; Context (archaeology); Variable (mathematics); Artificial neural network; Process (computing); Encoder; Machine learning; Task (project management); Mathematics; Engineering","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":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.001197793,0.0005105379,0.0006759178,0.0001634506,0.0006116684,0.001222425,0.006146485,0.0004221719,0.0000112621],"category_scores_gemma":[0.001175459,0.0004065935,0.0003343269,0.0001328852,0.000279113,0.0004067091,0.003330733,0.001028088,0.00001402307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001027488,"about_ca_system_score_gemma":0.000663186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001077328,"about_ca_topic_score_gemma":0.0000268421,"domain_scores_codex":[0.9962401,0.00002573724,0.001036295,0.001345112,0.0006992769,0.0006534617],"domain_scores_gemma":[0.9961873,0.0001622212,0.001105248,0.001171963,0.00121808,0.0001551523],"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":[0.00003879926,0.0001213537,0.00002866995,0.0002255302,0.00004103206,3.149701e-7,0.002262543,0.06282789,0.009158833,0.8904637,0.000149268,0.0346821],"study_design_scores_gemma":[0.00001913088,0.00003724152,0.000002073782,0.0003444214,0.00001787257,0.000001204285,0.00001760585,0.5471921,0.02145899,0.4306555,0.00001608169,0.0002378015],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01240939,0.00004859458,0.9778567,0.003849672,0.001323567,0.001122729,0.00004055525,0.0001457832,0.003203035],"genre_scores_gemma":[0.7435789,0.00005196902,0.2549351,0.0002291585,0.0003051507,0.0002449751,0.000003357354,0.00002990152,0.0006215897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7311695,"threshold_uncertainty_score":0.9998386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2165077802991398,"score_gpt":0.3321390255953345,"score_spread":0.1156312452961947,"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."}}