{"id":"W4233063693","doi":"10.3138/cmlr.63.1.59","title":"How Large a Vocabulary is Needed For Reading and Listening?","year":2006,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":1422,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Cambridge","keywords":"Vocabulary; Reading comprehension; Computer science; Active listening; Linguistics; Word (group theory); Reading (process); Comprehension; Natural language processing; Artificial intelligence; Listening comprehension; Psychology; Communication","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":[0.001355618,0.0002558739,0.0004558107,0.0009650191,0.0007330326,0.001934385,0.0005721495,0.0006684574,0.005009652],"category_scores_gemma":[0.01655594,0.0002125065,0.0001859644,0.0006957849,0.002496774,0.005831023,0.0008305577,0.0007137603,0.001585357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054094,"about_ca_system_score_gemma":0.002108652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01786729,"about_ca_topic_score_gemma":0.02318191,"domain_scores_codex":[0.9987127,0.0003592995,0.0001028993,0.0001990833,0.0004261569,0.0001999463],"domain_scores_gemma":[0.9942209,0.002891957,0.0007112531,0.0004565336,0.001194732,0.0005247778],"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":[0.0007173023,0.0001538164,0.06754673,0.001476845,0.0001450425,0.001805225,0.02249083,0.0005851242,0.06492617,0.05127517,0.01201531,0.7768625],"study_design_scores_gemma":[0.0002044087,0.00148615,0.5823577,0.001445869,0.0003183729,0.007109805,0.05092324,0.001366651,0.02439835,0.1634609,0.1666535,0.0002751572],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8024155,0.02042595,0.01401529,0.01733402,0.0005228519,0.0001326663,0.0007083469,0.0003598924,0.1440855],"genre_scores_gemma":[0.9827667,0.005087093,0.005843978,0.0007777167,0.0001953741,0.00007584497,0.0003941647,0.0001349427,0.004724021],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01786729,"threshold_uncertainty_score":0.03552657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01101669428534497,"score_gpt":0.2542969430756896,"score_spread":0.2432802487903447,"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."}}