{"id":"W4233783659","doi":"10.26686/wgtn.12552221.v1","title":"How large a vocabulary is needed for reading and listening?","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Victoria University; Victoria University of Wellington","keywords":"Vocabulary; Linguistics; Reading comprehension; Computer science; Active listening; Word (group theory); Comprehension; Reading (process); Natural language processing; Artificial intelligence; Psychology; Communication","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002496197,0.0002797049,0.0003524352,0.0001257656,0.0001190221,0.00138459,0.001232061,0.0002989313,0.000002846625],"category_scores_gemma":[0.0001914143,0.0002422546,0.0001164767,0.0001616177,0.00002560603,0.0003523917,0.003201832,0.0004971674,0.000001200819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003729728,"about_ca_system_score_gemma":0.00008672065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004148364,"about_ca_topic_score_gemma":0.000003028437,"domain_scores_codex":[0.9984086,0.00002627532,0.0001805487,0.0008631973,0.0002083903,0.0003129538],"domain_scores_gemma":[0.9988914,0.00008417417,0.0001700112,0.0006024058,0.0001309254,0.0001210668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007245608,0.0001065981,0.0002402567,0.004907794,0.0003076606,0.0002235849,0.02051932,8.457708e-7,0.01265763,0.5958771,0.2124573,0.1526294],"study_design_scores_gemma":[0.0006895207,0.0001970307,0.00001512112,0.0007609982,0.00007450061,0.00007032372,0.00028522,0.2557169,0.1057966,0.6036823,0.03121394,0.001497541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002330718,0.002875373,0.9661307,0.02820211,0.0002081562,0.0005001733,0.00002164157,0.001473706,0.0003550498],"genre_scores_gemma":[0.0830474,0.00002845746,0.9100553,0.004990362,0.0001558836,0.00008367544,0.00001820807,0.00002597951,0.001594715],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.255716,"threshold_uncertainty_score":0.9996521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02220495768745766,"score_gpt":0.2839526646534613,"score_spread":0.2617477069660036,"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."}}