{"id":"W4296671721","doi":"10.48550/arxiv.1607.00070","title":"A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue\\n Systems","year":2016,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hôtel-Dieu de Montréal","funders":"","keywords":"Computer science; Sequence (biology); Granularity; Action (physics); Encoder; Artificial intelligence; Space (punctuation); Artificial neural network; Human–computer interaction; Natural language processing; Programming language","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":[0.002017055,0.0008360923,0.0009140758,0.0005294154,0.0005232694,0.001114109,0.001496391,0.001616765,0.003471243],"category_scores_gemma":[0.006328191,0.0007112524,0.001112373,0.000433592,0.0008452471,0.001827752,0.001325558,0.002364673,0.001540465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001409109,"about_ca_system_score_gemma":0.001391819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01338991,"about_ca_topic_score_gemma":0.01548704,"domain_scores_codex":[0.9982377,0.0008876032,0.0001038638,0.0004626371,0.0001868642,0.0001212729],"domain_scores_gemma":[0.9970971,0.00209098,0.0001255515,0.0002746611,0.0002905407,0.0001212691],"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":[0.0005409613,0.000165518,0.002828546,0.0001287824,0.00009876163,0.0001751038,0.0007109725,0.906983,0.005810489,0.01814013,0.002739654,0.06167805],"study_design_scores_gemma":[0.000006637662,0.00002841775,0.0001135447,0.000002746305,0.000004434879,0.00001243404,0.000008254364,0.9958371,0.0003658888,0.003288366,0.0003265628,0.000005725046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09041592,0.0004560993,0.9008133,0.0008582349,0.0001235155,0.0001992288,0.001242417,0.003156412,0.00273478],"genre_scores_gemma":[0.8729133,0.000241705,0.1173546,0.0002705832,0.0000857865,0.0005063356,0.001774224,0.0002908992,0.006562699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01338991,"threshold_uncertainty_score":0.02662396,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2020256500661708,"score_gpt":0.2445606726865914,"score_spread":0.04253502262042058,"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."}}