{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001468492,0.0007942754,0.0006651655,0.0003394577,0.0003696391,0.0004371692,0.0008737143,0.0006233209,0.002020854],"category_scores_gemma":[0.003628606,0.0002192453,0.0004371327,0.0002383119,0.0004928224,0.0006371985,0.0007341355,0.0006436804,0.0003871392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005010432,"about_ca_system_score_gemma":0.000591707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002571673,"about_ca_topic_score_gemma":0.001738253,"domain_scores_codex":[0.9990867,0.0004074133,0.00004201338,0.0002447686,0.0001277381,0.00009119065],"domain_scores_gemma":[0.9988818,0.0006569501,0.00007038366,0.00006852692,0.0002596291,0.00006275486],"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":[0.0008082118,0.0004518546,0.003556014,0.0003161482,0.00009699278,0.0004286879,0.001024463,0.4459967,0.03557905,0.009401543,0.004537153,0.4978032],"study_design_scores_gemma":[0.0000363793,0.0000680064,0.0002452653,0.000003509037,0.00001297202,0.00003502282,0.00002535679,0.99449,0.00328378,0.001269833,0.0005205055,0.000009357199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1173249,0.0002377921,0.8753578,0.0002677417,0.00008472396,0.0002359459,0.00005314586,0.002307124,0.004130812],"genre_scores_gemma":[0.891035,0.00007962604,0.1050537,0.0001604234,0.00002780201,0.0002750675,0.0001079187,0.000092089,0.003168287],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002571673,"threshold_uncertainty_score":0.007766247,"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."}}