{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003448907,0.0001101894,0.0001359791,0.000156237,0.0002345223,0.0002404617,0.000227839,0.00006742527,0.000002170097],"category_scores_gemma":[0.0000394277,0.0001082419,0.00003518666,0.000242289,0.00001488288,0.0003970711,0.0001876509,0.00005634142,0.000003475767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006546469,"about_ca_system_score_gemma":0.00009029089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006458641,"about_ca_topic_score_gemma":0.00001663885,"domain_scores_codex":[0.9988827,0.00003141715,0.0002319514,0.0003813699,0.0001936941,0.0002789179],"domain_scores_gemma":[0.9993553,0.0001445172,0.0000635141,0.0002404695,0.0001094367,0.00008678383],"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":[0.00002287277,0.00009737327,0.4889936,0.0008613831,0.0001915545,0.00007506427,0.04513468,0.2801051,0.01969434,0.1340864,0.002274625,0.02846292],"study_design_scores_gemma":[0.0003207025,0.00000777954,0.001156829,0.00003070397,0.000005523848,0.00001142995,0.00126082,0.9954103,0.001466023,0.0001340438,0.00005236866,0.0001435138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5064324,0.00002199197,0.4924332,0.0001423872,0.0006820573,0.0001510551,0.000006754999,0.0001219049,0.000008214686],"genre_scores_gemma":[0.9731032,0.000001573907,0.02643398,0.0001305828,0.000162604,0.00002436006,0.00001184585,0.00001196884,0.0001199264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7153051,"threshold_uncertainty_score":0.4413978,"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."}}