{"id":"W3184197775","doi":"10.1145/3446390","title":"Chinese Emotional Dialogue Response Generation via Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Internet Technology","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Expression (computer science); Artificial intelligence; Function (biology); Quality (philosophy); Key (lock); Process (computing); Reinforcement; Machine learning; Psychology; Social 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":[0.0001940835,0.0001389824,0.0001364984,0.0003580077,0.000129805,0.00005903273,0.0006807621,0.0001789501,0.0001821686],"category_scores_gemma":[0.0001869511,0.0001410277,0.00007346796,0.0005210746,0.00004323805,0.0002069163,0.00006118498,0.0004444038,0.000125867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001158718,"about_ca_system_score_gemma":0.00007237291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002039379,"about_ca_topic_score_gemma":0.00005397883,"domain_scores_codex":[0.9987815,0.000108239,0.0002706337,0.0004428659,0.0001812553,0.0002154807],"domain_scores_gemma":[0.9988574,0.00009875098,0.00005922563,0.0008296911,0.000113978,0.00004098806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001277349,0.0003219128,0.0006795487,0.00001739631,0.0001802217,0.0001909312,0.001421047,0.3748348,0.1113959,0.03235633,0.0002276278,0.4782465],"study_design_scores_gemma":[0.0005971653,0.0003438439,0.0003298756,0.00003196449,0.000009835243,0.000314298,0.00004238111,0.8997968,0.08604215,0.00823552,0.003976744,0.0002793765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1519866,0.00002902348,0.8407629,0.006087011,0.0005559191,0.00006911936,6.473331e-7,0.0004123671,0.00009639237],"genre_scores_gemma":[0.9463242,0.00001549887,0.05123544,0.0002712387,0.00004378416,0.0000332106,0.000009058739,0.000009825678,0.002057778],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7943376,"threshold_uncertainty_score":0.5750941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01830692526542982,"score_gpt":0.2617962720293058,"score_spread":0.243489346763876,"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."}}