{"id":"W2119652412","doi":"10.3138/cmlr.1726.436","title":"A Corpus-Based Assessment of French CEFR Lexical Content","year":2013,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Vocabulary; Computer science; Corpus linguistics; Natural language processing; Intuition; Artificial intelligence; Introspection; Vocabulary development; Perspective (graphical); Linguistics; Psychology; Cognitive psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005536477,0.0003982261,0.0007503888,0.0003850948,0.0001241398,0.0001528743,0.001570967,0.0001691503,0.0001858371],"category_scores_gemma":[0.0006013308,0.0003489198,0.0002316374,0.0006135003,0.0002407328,0.0004378384,0.0001231491,0.0003837081,0.00002292887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007257374,"about_ca_system_score_gemma":0.0006985216,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2645862,"about_ca_topic_score_gemma":0.191909,"domain_scores_codex":[0.9973777,0.0002286961,0.0006172918,0.0006361068,0.0002020104,0.000938231],"domain_scores_gemma":[0.9968398,0.0002342348,0.0002955679,0.001145087,0.0005127093,0.0009726617],"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":[0.000005755101,0.0002745854,0.01005399,0.01624548,0.0003050314,0.004049678,0.009584783,0.00003327999,0.1460164,0.05491215,0.01154295,0.7469759],"study_design_scores_gemma":[0.005990268,0.002794118,0.2147559,0.110607,0.001245531,0.00554507,0.002277535,0.424174,0.04106177,0.09153683,0.08591216,0.01409982],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.2907069,0.4523547,0.2396892,0.007185888,0.0005055423,0.003380968,0.0005865192,0.001029206,0.00456111],"genre_scores_gemma":[0.8315977,0.001253683,0.1637959,0.002476996,0.00008550725,0.000158321,0.00009947407,0.00005375864,0.000478661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7328761,"threshold_uncertainty_score":0.9998963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02157208107470289,"score_gpt":0.2600412722368445,"score_spread":0.2384691911621416,"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."}}