{"id":"W2624448691","doi":"10.18653/v1/w17-2626","title":"A Frame Tracking Model for Memory-Enhanced Dialogue Systems","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Utterance; Frame (networking); Computer science; Task (project management); Tracking (education); Set (abstract data type); Baseline (sea); State (computer science); Artificial intelligence; Algorithm; Telecommunications; Programming language; Engineering","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009510412,0.0004910065,0.000883543,0.0001887512,0.0003535766,0.002152328,0.003887706,0.0007118724,0.000002398374],"category_scores_gemma":[0.0003549211,0.000436708,0.0004175105,0.00005878894,0.00005671917,0.0004799212,0.001403102,0.0005010688,0.00008057103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001331665,"about_ca_system_score_gemma":0.0006015137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008673079,"about_ca_topic_score_gemma":0.0001536874,"domain_scores_codex":[0.996782,0.00008506604,0.0006495442,0.001311218,0.0004846912,0.0006874471],"domain_scores_gemma":[0.9953295,0.0002073331,0.0006791096,0.003145676,0.0003906483,0.0002477169],"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":[0.0001639836,0.000470265,0.00005403105,0.005828056,0.0007601713,0.00007123022,0.01364786,0.5889265,0.007347011,0.2594075,0.05131081,0.07201262],"study_design_scores_gemma":[0.0004925392,0.00003525382,0.00001402921,0.0003273343,0.00001952944,0.000007296358,0.00002917898,0.9677821,0.001659109,0.02872642,0.0003232782,0.0005838755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009469806,0.0005502498,0.9687843,0.0002542708,0.008811234,0.002062837,0.00009293517,0.0006606965,0.01783647],"genre_scores_gemma":[0.9375606,0.00002169704,0.05466845,0.0001290692,0.001116256,0.0009599099,0.00006776359,0.00004546652,0.00543085],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9366136,"threshold_uncertainty_score":0.9998085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07295084213083664,"score_gpt":0.3025950117516825,"score_spread":0.2296441696208459,"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."}}