{"id":"W4385572402","doi":"10.18653/v1/2023.bea-1.43","title":"CEFR-based Contextual Lexical Complexity Classifier in English and French","year":2023,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"CBC (Canada)","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Classifier (UML); Perspective (graphical); Lexical choice; Lexical item; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001316154,0.001287651,0.0009161562,0.003838303,0.0008476881,0.001937591,0.001074271,0.001427675,0.004254028],"category_scores_gemma":[0.005897699,0.0001865747,0.001029818,0.00136372,0.0004074257,0.002291688,0.001130706,0.001217395,0.003017863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001313837,"about_ca_system_score_gemma":0.001090276,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02040662,"about_ca_topic_score_gemma":0.02713661,"domain_scores_codex":[0.9983861,0.000298061,0.0001136081,0.000640123,0.0003576981,0.0002043901],"domain_scores_gemma":[0.9974994,0.001189952,0.000127706,0.0002405807,0.0008156903,0.0001266303],"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":[0.001834958,0.0005216733,0.03585026,0.0007880737,0.0003562854,0.001445278,0.0008744816,0.03359141,0.04065268,0.008045476,0.03237783,0.8436615],"study_design_scores_gemma":[0.0001381476,0.0005500442,0.05291402,0.0002823479,0.0003359026,0.001864296,0.001605448,0.8431262,0.03676894,0.008385689,0.05382792,0.0002010707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.566736,0.006638207,0.3565034,0.001277909,0.0006094053,0.0005867159,0.01193394,0.02090146,0.03481307],"genre_scores_gemma":[0.8378398,0.0006630863,0.1327435,0.0003195165,0.0002106288,0.0003146846,0.01801548,0.0005391198,0.009354249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02040662,"threshold_uncertainty_score":0.04057562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07541358480765059,"score_gpt":0.2832977846667575,"score_spread":0.2078841998591069,"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."}}