{"id":"W4225331178","doi":"10.46298/jdmdh.9123","title":"Towards an empirical evaluation of translated texts and translation quality","year":2022,"lang":"en","type":"article","venue":"Journal of Data Mining & Digital Humanities","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Phraseology; Source text; Artificial intelligence; Context (archaeology); Quality (philosophy); Translation (biology); Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002268384,0.00008908728,0.0001953285,0.0002092239,0.0001271307,0.0003133272,0.001040233,0.00002705062,0.00001729089],"category_scores_gemma":[0.0001166688,0.00007989495,0.00003420454,0.0001732034,0.00007056045,0.005522678,0.000215491,0.0001833609,7.177104e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004114087,"about_ca_system_score_gemma":0.0002130546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001123349,"about_ca_topic_score_gemma":0.00001045333,"domain_scores_codex":[0.9980587,0.0002118633,0.0005065902,0.0001752481,0.0009491388,0.00009844533],"domain_scores_gemma":[0.9988436,0.0001044358,0.0004080652,0.0003251907,0.000283728,0.00003501433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004367443,0.0001123937,0.0003142122,0.00003240914,0.0000293202,0.000007852225,0.0153134,0.00001224003,0.0003311523,0.0009197293,0.0001575381,0.9827261],"study_design_scores_gemma":[0.01369329,0.01543895,0.03766876,0.001314362,0.001270867,0.00422514,0.0393723,0.400887,0.01436901,0.4404227,0.02744562,0.003892008],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9242461,0.007708358,0.06603236,0.0004072322,0.000161658,0.0001528896,0.0002706218,0.00009354719,0.0009272692],"genre_scores_gemma":[0.9216195,0.000005597895,0.07821501,0.00004378942,0.00003625069,0.000001376283,0.00006556122,0.00000610572,0.000006835634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9788341,"threshold_uncertainty_score":0.4003808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2710737773030953,"score_gpt":0.4273664435802014,"score_spread":0.156292666277106,"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."}}