{"id":"W3099289136","doi":"10.18653/v1/2020.findings-emnlp.142","title":"Neural Dialogue State Tracking with Temporally Expressive Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Beijing Advanced Innovation Center for Big Data and Brain Computing; Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; National Natural Science Foundation of China","keywords":"Computer science; Graphical model; Expressive power; State (computer science); Probabilistic logic; Tracking (education); Feature (linguistics); Artificial intelligence; Recurrent neural network; Artificial neural network; Natural language processing; Machine learning; Theoretical computer science; Algorithm","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":[0.001332877,0.0009671219,0.0006036711,0.0006835949,0.0004218348,0.0007903512,0.001146743,0.0008958683,0.001249539],"category_scores_gemma":[0.004470672,0.0005037779,0.0005659749,0.0006344495,0.0004256754,0.001668338,0.001222386,0.001856444,0.0005168223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009098375,"about_ca_system_score_gemma":0.0006591612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01091789,"about_ca_topic_score_gemma":0.01633673,"domain_scores_codex":[0.9991629,0.0002567804,0.0000379188,0.000362074,0.0001061029,0.00007425883],"domain_scores_gemma":[0.9987425,0.0007765727,0.0001326166,0.0001266484,0.00017545,0.00004609968],"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":[0.0004789112,0.000193314,0.002323226,0.0001048077,0.0001458611,0.000128083,0.0002681675,0.661997,0.009469459,0.007648593,0.00380529,0.3134374],"study_design_scores_gemma":[0.000004129716,0.00001246737,0.000154621,0.000004550397,0.000008431523,0.000007690194,0.000006413166,0.9963605,0.0007073879,0.002402887,0.000326194,0.000004701526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0723341,0.001312205,0.9186788,0.0004293563,0.0001475048,0.00006284195,0.0007005545,0.00290263,0.003431919],"genre_scores_gemma":[0.8823352,0.000350549,0.1112653,0.0002066012,0.00008192235,0.0001304489,0.001242798,0.0001288981,0.004258221],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01091789,"threshold_uncertainty_score":0.02170873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02215996736713131,"score_gpt":0.2096675132888617,"score_spread":0.1875075459217304,"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."}}