{"id":"W4390898156","doi":"","title":"For a common European framework for evaluating AI- based translation technologies","year":2023,"lang":"en","type":"book-chapter","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Translation (biology); Computer science; Artificial intelligence; Biology","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":[0.1237089,0.002799106,0.002960738,0.01789521,0.004490853,0.02534691,0.006461356,0.008289677,0.03269955],"category_scores_gemma":[0.1333643,0.0008082477,0.003828537,0.01670367,0.004717243,0.02324386,0.01266483,0.005169288,0.01206254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01003139,"about_ca_system_score_gemma":0.01394014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01198852,"about_ca_topic_score_gemma":0.009529941,"domain_scores_codex":[0.8584448,0.08386044,0.01741294,0.006363979,0.03008481,0.003833004],"domain_scores_gemma":[0.8657932,0.03962196,0.007535502,0.02715244,0.05544238,0.004454511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001296923,0.001090778,0.004434717,0.00243815,0.0006797273,0.0002973379,0.00188529,0.01183501,0.007591072,0.5105687,0.07108238,0.3867999],"study_design_scores_gemma":[0.000762885,0.002654525,0.01646647,0.01068977,0.001273656,0.0007847895,0.006498107,0.03887071,0.02285959,0.3401791,0.5583947,0.0005655987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02508356,0.01093875,0.5848027,0.01668283,0.003127502,0.005891238,0.01239292,0.00524921,0.3358313],"genre_scores_gemma":[0.1705356,0.003331645,0.7556155,0.003565487,0.0005107002,0.005911591,0.02344571,0.003144273,0.03393948],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1237089,"threshold_uncertainty_score":0.6542431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0442397373322956,"score_gpt":0.3008759690727311,"score_spread":0.2566362317404355,"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."}}