{"id":"W4224279631","doi":"10.18653/v1/2022.naacl-main.426","title":"Less is More: Learning to Refine Dialogue History for Personalized Dialogue Generation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","topic":"Topic Modeling","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"Renmin University of China; National Natural Science Foundation of China","keywords":"Computer science; Computational linguistics; Human language; Natural language processing; Association (psychology); Artificial intelligence; Cognitive science; Linguistics; Psychology; Philosophy; Epistemology","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":[0.002686424,0.001797343,0.001044718,0.001484534,0.0009313307,0.001417909,0.002260451,0.001548191,0.009601868],"category_scores_gemma":[0.01470452,0.0009439407,0.0008111023,0.0006944911,0.0007053992,0.004302833,0.002831999,0.001904396,0.003241534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007743838,"about_ca_system_score_gemma":0.001077656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003864367,"about_ca_topic_score_gemma":0.007213588,"domain_scores_codex":[0.9979151,0.0008988633,0.00008624118,0.0007497846,0.0002002061,0.0001498285],"domain_scores_gemma":[0.9936404,0.004583235,0.0002219109,0.0006880116,0.0005360877,0.0003304275],"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":[0.001428621,0.0004309918,0.003797319,0.000400436,0.0001166995,0.0001560222,0.001448591,0.02119747,0.01051189,0.003750376,0.02294403,0.9338176],"study_design_scores_gemma":[0.000375597,0.0004250806,0.002684669,0.0001087602,0.0001989336,0.0002055199,0.0006882646,0.9393814,0.01162189,0.03158318,0.012641,0.00008579755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06361929,0.002641474,0.899855,0.001223054,0.0005296387,0.0005255822,0.001435827,0.02256947,0.007600781],"genre_scores_gemma":[0.6413783,0.0005269369,0.3450539,0.0005945992,0.0002594467,0.000633022,0.0037114,0.001217032,0.006625399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009601868,"threshold_uncertainty_score":0.03212142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03673297298027899,"score_gpt":0.2583922274011966,"score_spread":0.2216592544209176,"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."}}