{"id":"W4303437283","doi":"10.7202/1092190ar","title":"Revisiting simplification in corpus-based translation studies: Insights from readability research","year":2022,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Readability; Computer science; Natural language processing; Linguistics; Artificial intelligence; Set (abstract data type); Sentence; Vocabulary","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005677468,0.0001737854,0.0003919407,0.0004707641,0.001148846,0.0002473088,0.001067846,0.00004883869,0.00004459025],"category_scores_gemma":[0.0007047323,0.0001550102,0.0001845839,0.001861768,0.0002003316,0.0008999239,0.00009228622,0.001061026,0.000006649544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006582049,"about_ca_system_score_gemma":0.0002234132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001338742,"about_ca_topic_score_gemma":0.00006530516,"domain_scores_codex":[0.9936767,0.003457011,0.0008084956,0.000618781,0.001071943,0.0003671055],"domain_scores_gemma":[0.9967119,0.001723754,0.0002577466,0.0007697422,0.0004096903,0.0001271775],"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":[0.00009659707,0.0003653269,0.003617491,0.00006136671,0.0001785609,0.00003564787,0.004454503,0.005876519,0.01555892,0.01000498,0.00007119563,0.9596789],"study_design_scores_gemma":[0.001210879,0.000509745,0.1697516,0.00009440492,0.0002102047,0.00009488661,0.001476414,0.04960646,0.007966699,0.7181695,0.05018804,0.0007212292],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7926846,0.05244048,0.1493547,0.004594233,0.0003324174,0.0004545285,0.0000118495,0.00008701954,0.00004020632],"genre_scores_gemma":[0.9787678,0.001797146,0.01907118,0.0001114335,0.000111165,0.00009629436,0.00001827877,0.00001404902,0.00001268461],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9589577,"threshold_uncertainty_score":0.883611,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2309234669878421,"score_gpt":0.3783169797667931,"score_spread":0.147393512778951,"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."}}