{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009988922,0.0004316427,0.0006498943,0.000476016,0.00006949968,0.0004443165,0.001981108,0.0004949858,0.000002700706],"category_scores_gemma":[0.0002852135,0.0003417061,0.0001798244,0.0002961859,0.00003601074,0.0004952043,0.0009902604,0.0002374382,0.0001549171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004949947,"about_ca_system_score_gemma":0.00065355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001173343,"about_ca_topic_score_gemma":0.0003506074,"domain_scores_codex":[0.9965642,0.000135603,0.0008153752,0.001313045,0.0004876517,0.0006840891],"domain_scores_gemma":[0.9971589,0.0004085311,0.000283935,0.001557632,0.0003214705,0.0002694626],"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":[0.00003204513,0.00003291371,0.0004201921,0.0002233857,0.00001654571,0.00001349494,0.0006544591,0.9450304,0.0007744736,0.05064407,0.00071967,0.001438368],"study_design_scores_gemma":[0.0004612155,0.00003994272,0.00007905931,0.0004586738,0.000004932832,0.000003718303,0.000008974626,0.9678767,0.0001217172,0.02989766,0.0005526657,0.0004946875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006203383,0.00007122324,0.9852053,0.0004894975,0.002499142,0.00303504,0.000217297,0.0003483199,0.001930814],"genre_scores_gemma":[0.962143,0.000006617257,0.03399941,0.0002597886,0.0004065335,0.0009922602,0.00005700186,0.00003405265,0.002101316],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9559397,"threshold_uncertainty_score":0.9999035,"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."}}