{"id":"W4362700380","doi":"10.1007/s11227-023-05209-z","title":"Exploring implicit persona knowledge for personalized dialogue generation","year":2023,"lang":"en","type":"article","venue":"The Journal of Supercomputing","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"National Social Science Fund of China","keywords":"Persona; Computer science; Consistency (knowledge bases); Key (lock); Human–computer interaction; Style (visual arts); World Wide Web; Data science; Artificial intelligence","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":[0.002639675,0.0009331778,0.0007575239,0.001204009,0.0009692707,0.002506105,0.00156671,0.001931295,0.007351538],"category_scores_gemma":[0.01639162,0.0007239473,0.0009968674,0.000847983,0.0006129392,0.004629547,0.002796879,0.002504197,0.002523515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006743242,"about_ca_system_score_gemma":0.0009519826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003028693,"about_ca_topic_score_gemma":0.003772176,"domain_scores_codex":[0.9973341,0.001478395,0.0000992689,0.0006113278,0.0003105088,0.000166388],"domain_scores_gemma":[0.9912747,0.007091945,0.0001886739,0.0006396272,0.0005878304,0.0002172348],"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":[0.002370029,0.0009898508,0.01198864,0.001085673,0.0004453377,0.0009255678,0.009680212,0.07343304,0.0304,0.03872962,0.02017899,0.809773],"study_design_scores_gemma":[0.00008560994,0.0001777242,0.002099799,0.0001143742,0.0001521346,0.0003082847,0.001261695,0.9256582,0.009331107,0.04984784,0.01089067,0.00007254494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07905271,0.0008498185,0.9058319,0.00099317,0.0002196532,0.0002251095,0.0009672817,0.00390097,0.007959268],"genre_scores_gemma":[0.824898,0.0003311248,0.1669122,0.0002174782,0.0001308753,0.0002256558,0.002080644,0.0004562212,0.004747786],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007351538,"threshold_uncertainty_score":0.02459335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2566185109295542,"score_gpt":0.3163193920778916,"score_spread":0.05970088114833738,"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."}}