{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007447587,0.0004523646,0.0005255811,0.01650424,0.001677536,0.002576657,0.0008307952,0.0006048382,0.005256732],"category_scores_gemma":[0.02769049,0.0001789017,0.0002672052,0.01024077,0.001151682,0.001792804,0.001747564,0.000499293,0.001129698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003260073,"about_ca_system_score_gemma":0.002750884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.09098182,"about_ca_topic_score_gemma":0.091054,"domain_scores_codex":[0.9949806,0.002188992,0.0003804519,0.000754111,0.001519002,0.0001767436],"domain_scores_gemma":[0.9780471,0.008535112,0.001449023,0.001782869,0.009825972,0.0003599614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0008620133,0.0002891267,0.1896079,0.003961731,0.0003373768,0.001611157,0.05053228,0.002797818,0.02541105,0.0244277,0.04877798,0.6513838],"study_design_scores_gemma":[0.0001231227,0.0004929933,0.5835086,0.002026281,0.0003354579,0.003292848,0.03695297,0.009664577,0.01635749,0.00329675,0.3437313,0.0002178231],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8824684,0.007132906,0.0224223,0.001229238,0.0001810581,0.0006353347,0.02097238,0.0006433256,0.06431507],"genre_scores_gemma":[0.948799,0.001749623,0.02440949,0.0001654126,0.0000849538,0.0006108682,0.01950417,0.0001887662,0.004487805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09098182,"threshold_uncertainty_score":0.1809044,"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."}}