{"id":"W4404783453","doi":"10.18653/v1/2024.emnlp-main.294","title":"Beyond Reference: Evaluating High Quality Translations Better than Human References","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Hanyang University","keywords":"Computer science; Quality (philosophy)","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":[0.01244183,0.002007083,0.001505727,0.005285842,0.0009511839,0.002996405,0.001349515,0.002750588,0.005184071],"category_scores_gemma":[0.05519284,0.0003271084,0.0007905761,0.003609765,0.001302026,0.004516361,0.002151936,0.0007996605,0.002368082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008389057,"about_ca_system_score_gemma":0.001042808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002436817,"about_ca_topic_score_gemma":0.004682778,"domain_scores_codex":[0.9834366,0.008458544,0.001663203,0.00247955,0.003675452,0.0002866542],"domain_scores_gemma":[0.9619023,0.02238099,0.003321653,0.0033769,0.008065453,0.0009525765],"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":[0.005742533,0.001053639,0.05181487,0.005270316,0.001832334,0.001380877,0.004187248,0.03670145,0.09492311,0.007100932,0.01939841,0.7705943],"study_design_scores_gemma":[0.001656573,0.01634717,0.1841924,0.001179289,0.003530591,0.006202987,0.005253524,0.4604274,0.2014998,0.03990576,0.0785658,0.001238656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6565755,0.01634513,0.2848978,0.000767251,0.000841756,0.001433036,0.004761206,0.00872114,0.0256572],"genre_scores_gemma":[0.8590074,0.001032574,0.1284635,0.0003758124,0.0002535324,0.0004110953,0.005490112,0.001030783,0.003935167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01244183,"threshold_uncertainty_score":0.06579947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09457329550499463,"score_gpt":0.4161355212544516,"score_spread":0.321562225749457,"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."}}