{"id":"W2952100657","doi":"10.18653/v1/p19-2027","title":"Dialogue-Act Prediction of Future Responses Based on Conversation History","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Japan Society for the Promotion of Science; Microsoft Research Asia; Microsoft Research","keywords":"Computer science; Utterance; Conversation; Focus (optics); Sequence (biology); Process (computing); Baseline (sea); Artificial intelligence; Chatbot; Recurrent neural network; Speech recognition; Artificial neural network; Machine learning; Natural language processing; Psychology","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":[0.0001867711,0.00004744496,0.0000700169,0.00008418004,0.000009403789,0.000005924956,0.0001738604,0.00004520864,0.0000975248],"category_scores_gemma":[0.00001874146,0.0000419828,0.00002832621,0.00005066388,0.000008825236,0.0001638427,0.00001960799,0.0000512769,0.00003733377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001173719,"about_ca_system_score_gemma":0.00009571039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002158298,"about_ca_topic_score_gemma":0.000001274378,"domain_scores_codex":[0.9994233,0.00005662893,0.0001134413,0.0001658635,0.0001754749,0.00006532062],"domain_scores_gemma":[0.9994438,0.00008576185,0.00005362098,0.0003594332,0.00003524515,0.00002218082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008424676,0.0005164453,0.3459455,0.0004131656,0.0000872023,0.00001069216,0.01525868,0.03242005,0.1383778,0.2445771,0.02515695,0.1963939],"study_design_scores_gemma":[0.0004321012,0.0001937111,0.04650095,0.00001503449,0.000002840498,4.006272e-7,0.00002843228,0.9321362,0.002316736,0.0001118855,0.01819042,0.00007130136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2342834,0.00002216999,0.7572693,0.0009156538,0.001744409,0.000143136,0.000002487944,0.0001334893,0.005485892],"genre_scores_gemma":[0.9896432,0.000001202719,0.009315822,0.0002975836,0.00008857479,0.000001852895,0.000003327173,0.000002610806,0.0006458191],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8997161,"threshold_uncertainty_score":0.1712009,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02220982018352012,"score_gpt":0.2075698187986197,"score_spread":0.1853599986150996,"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."}}