{"id":"W4385570832","doi":"10.18653/v1/2023.findings-acl.896","title":"DEnsity: Open-domain Dialogue Evaluation Metric using Density Estimation","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Metric (unit); Computer science; Classifier (UML); Artificial intelligence; Feature vector; Feature (linguistics); Machine learning; Density estimation; Domain (mathematical analysis); Open domain; Pattern recognition (psychology); Mathematics; Statistics","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":[0.007269303,0.001840512,0.001369394,0.003603896,0.0006382561,0.001848047,0.001305377,0.001788629,0.001976847],"category_scores_gemma":[0.04824638,0.0002960192,0.0007178597,0.001568788,0.001074882,0.004007856,0.002604358,0.001728995,0.001218728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001337893,"about_ca_system_score_gemma":0.0009340593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002651721,"about_ca_topic_score_gemma":0.001901004,"domain_scores_codex":[0.988757,0.005602562,0.0008723614,0.00142267,0.002957372,0.0003881299],"domain_scores_gemma":[0.9678083,0.02088153,0.002429646,0.002260264,0.00565748,0.0009627814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002685792,0.001006608,0.05577647,0.00173859,0.0006817944,0.0004457373,0.002272663,0.1569954,0.02090228,0.02038791,0.02487444,0.7122324],"study_design_scores_gemma":[0.00009656521,0.001041653,0.02392014,0.0001715556,0.0001461205,0.0007510281,0.0006537737,0.9233988,0.01481599,0.02665351,0.008101658,0.0002492939],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1218982,0.003299602,0.8581152,0.0005874148,0.0002619894,0.0007076108,0.002256919,0.005415079,0.007457932],"genre_scores_gemma":[0.8667762,0.0004418031,0.1264796,0.0001826671,0.0001812702,0.0007644724,0.002772217,0.0003831927,0.002018457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007269303,"threshold_uncertainty_score":0.03844422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1344899496127179,"score_gpt":0.3537995330139125,"score_spread":0.2193095834011946,"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."}}