{"id":"W3017372818","doi":"10.18653/v1/2020.acl-main.56","title":"Gated Convolutional Bidirectional Attention-based Model for Off-topic Spoken Response Detection","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Recall; Task (project management); Relevance (law); Residual; Pattern recognition (psychology); Sampling (signal processing); Training set","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":[],"consensus_categories":[],"category_scores_codex":[0.0002697553,0.0001012791,0.0001015006,0.00007844449,0.0001531992,0.00005807115,0.0002716899,0.00006449228,0.00003254295],"category_scores_gemma":[0.0001429698,0.0001023931,0.00009988638,0.0002201968,0.00001906933,0.000225556,0.00005051877,0.00007828238,0.00003013221],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000763394,"about_ca_system_score_gemma":0.000211444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000108426,"about_ca_topic_score_gemma":0.000018611,"domain_scores_codex":[0.9989207,0.0000571595,0.0002147013,0.0003909522,0.0002327042,0.0001837418],"domain_scores_gemma":[0.9993188,0.0001634335,0.00005411226,0.0001939188,0.0001659898,0.000103768],"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":[0.00145343,0.0001714061,0.001474716,0.00007232319,0.00007879075,0.000005804797,0.0004079467,0.7956439,0.1050738,0.04775267,0.002784868,0.04508034],"study_design_scores_gemma":[0.0006579287,0.00006567451,0.001367919,0.000004363169,0.00000467615,0.000002145583,0.00000432017,0.9921671,0.002836856,0.001060577,0.001706859,0.0001216047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05839517,0.00002293856,0.9346556,0.006029485,0.0002209857,0.0002187819,0.000006703133,0.0003374149,0.0001128908],"genre_scores_gemma":[0.8923168,6.887968e-7,0.1052266,0.001415238,0.0001015062,0.00003562838,0.000006692633,0.000007520687,0.0008893909],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8339216,"threshold_uncertainty_score":0.4175471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04774598965152945,"score_gpt":0.2549896021022108,"score_spread":0.2072436124506813,"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."}}