{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003739664,0.00007670697,0.000117311,0.00009817025,0.00005922284,0.00009786453,0.000287332,0.00006702985,0.00003510292],"category_scores_gemma":[0.000155974,0.00006749146,0.00002469541,0.0004722322,0.0001871866,0.0002155948,0.0001048666,0.0001199187,0.00005177321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002949624,"about_ca_system_score_gemma":0.00005741371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003036839,"about_ca_topic_score_gemma":0.0008493196,"domain_scores_codex":[0.999066,0.00007699103,0.0001783355,0.0003242192,0.0001557038,0.0001987285],"domain_scores_gemma":[0.9992643,0.0002460979,0.00002202401,0.0003305604,0.00006127716,0.00007571455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000008387072,0.0001668264,0.04128593,0.0000255026,0.000004316646,0.00001061625,0.002183046,0.0000505652,0.0004386679,0.8937038,0.007599333,0.05452297],"study_design_scores_gemma":[0.0005989138,0.00006558084,0.7480597,0.000008557352,0.000001169343,0.000001214125,0.0001970728,0.2152529,0.0006232787,0.02565872,0.009349587,0.0001833071],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.774377,0.00002188381,0.2078981,0.007437794,0.000275347,0.0002623179,0.00000950897,0.0008324155,0.008885704],"genre_scores_gemma":[0.9956763,0.000001590524,0.00366407,0.0003164849,0.00002890071,0.00001238739,0.000009267393,0.000002654695,0.0002882945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8680451,"threshold_uncertainty_score":0.2752222,"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."}}