{"id":"W4392669929","doi":"10.18653/v1/2023.findings-ijcnlp.30","title":"Mixing It Up: Inducing Empathy and Politeness using Multiple Behaviour-aware Generators for Conversational Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Politeness; Computer science; Politeness theory; Encoder; Human–computer interaction; Generator (circuit theory); Empathy; Context (archaeology); Natural language processing; Artificial intelligence; Speech recognition; Psychology; Linguistics; 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":[0.00158394,0.0009926226,0.000523895,0.0006102336,0.0003889822,0.0009573491,0.0008750862,0.001071698,0.002901434],"category_scores_gemma":[0.006271462,0.0004492073,0.0008326363,0.0002917815,0.0006195525,0.001357927,0.001453572,0.001411251,0.001423032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006260509,"about_ca_system_score_gemma":0.0005684512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00136828,"about_ca_topic_score_gemma":0.002347162,"domain_scores_codex":[0.9985317,0.0008243088,0.00004799778,0.0003530779,0.000138712,0.0001042959],"domain_scores_gemma":[0.9976885,0.001667273,0.0001028297,0.0002592979,0.0001824471,0.00009957312],"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":[0.0009752189,0.000628599,0.00544935,0.0006527581,0.0002429083,0.0004813613,0.002304261,0.1152848,0.07398602,0.01798382,0.01411789,0.767893],"study_design_scores_gemma":[0.00005995631,0.0001568548,0.001223905,0.00002736176,0.00005161228,0.0001775444,0.0002307145,0.9620712,0.01396351,0.01702657,0.004977246,0.0000334074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05707694,0.0007086338,0.9323256,0.0004483999,0.0001411352,0.0002581392,0.0003443287,0.004858611,0.003838247],"genre_scores_gemma":[0.7479272,0.0003036162,0.2420695,0.0003755581,0.0001454157,0.0004114159,0.001677178,0.0006267109,0.006463313],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002901434,"threshold_uncertainty_score":0.009706259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09577259153113851,"score_gpt":0.2994427351005817,"score_spread":0.2036701435694432,"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."}}