{"id":"W2467764055","doi":"10.21437/interspeech.2016-1175","title":"A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Sequence (biology); Granularity; Action (physics); Encoder; Artificial intelligence; Space (punctuation); Human–computer interaction; Natural language processing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002889022,0.0009084408,0.001128125,0.0006485633,0.0005210979,0.001133364,0.001698967,0.001809272,0.002997437],"category_scores_gemma":[0.009346521,0.0007854084,0.001233783,0.0005808995,0.001052128,0.002247653,0.001342712,0.002717603,0.001616662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001200535,"about_ca_system_score_gemma":0.001372691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008409008,"about_ca_topic_score_gemma":0.008016919,"domain_scores_codex":[0.9971707,0.001592707,0.0001642547,0.000605967,0.0003243233,0.0001420826],"domain_scores_gemma":[0.9954074,0.003352167,0.0002106521,0.0004336997,0.0004462957,0.0001497873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005150783,0.0001634547,0.002197456,0.0001366938,0.0000903816,0.0001973574,0.0007196266,0.9107208,0.00647917,0.02356119,0.001866708,0.05335214],"study_design_scores_gemma":[0.000008368104,0.00004299013,0.0001113587,0.000003919539,0.000006020379,0.0000233413,0.000008620425,0.9937661,0.0004592529,0.005152007,0.0004105505,0.000007548713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04610136,0.0003045224,0.9486886,0.0004693471,0.00008274449,0.0001655244,0.0006497382,0.001908331,0.001629891],"genre_scores_gemma":[0.8363383,0.0003034164,0.1546054,0.0002557238,0.00009008807,0.0007270491,0.001472833,0.0003166688,0.005890548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008409008,"threshold_uncertainty_score":0.01672018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1132964661192446,"score_gpt":0.3325977584600825,"score_spread":0.219301292340838,"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."}}