{"id":"W3091315598","doi":"10.1109/ijcnn48605.2020.9207289","title":"Transformer Decoder Based Reinforcement Learning Approach for Conversational Response Generation","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Transformer; Conversation; Reinforcement learning; Artificial intelligence; Language model; Speech recognition; Natural language processing; Machine learning; Voltage; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002136096,0.0007836956,0.0008594168,0.0005286109,0.0003811482,0.0006907511,0.001819265,0.001203943,0.003980007],"category_scores_gemma":[0.006274174,0.0003984493,0.0006254325,0.0003574178,0.0008281635,0.001378591,0.001325364,0.001911696,0.001339765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009748608,"about_ca_system_score_gemma":0.00119172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003200214,"about_ca_topic_score_gemma":0.003569722,"domain_scores_codex":[0.9987316,0.0006829074,0.00004892498,0.0002738731,0.0001732044,0.00008946886],"domain_scores_gemma":[0.9975637,0.001673582,0.0001119415,0.0001679075,0.0003396644,0.0001432647],"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":[0.0005813607,0.0004113768,0.001786111,0.0002401437,0.0001013226,0.0002731549,0.0007025568,0.6733646,0.017733,0.02931938,0.00462939,0.2708576],"study_design_scores_gemma":[0.00001257634,0.00004771526,0.00005212384,0.000003557978,0.000007296863,0.00002339106,0.000012045,0.9935113,0.001397313,0.004377216,0.0005486692,0.000006845015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01801247,0.000233789,0.9773142,0.0003139872,0.00005883004,0.0001028468,0.0000851231,0.001538962,0.002339792],"genre_scores_gemma":[0.8152251,0.0002002874,0.1748154,0.0003602699,0.00007736863,0.0003584705,0.0002958259,0.0002452639,0.008422026],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003980007,"threshold_uncertainty_score":0.01331449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06948471122514176,"score_gpt":0.2595321422884425,"score_spread":0.1900474310633007,"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."}}