{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002739402,0.0004133313,0.0007928571,0.00184816,0.001114739,0.003258405,0.0009797818,0.001186826,0.009189421],"category_scores_gemma":[0.03135994,0.0004322343,0.0003599528,0.001453616,0.003331945,0.01313311,0.00158829,0.001276059,0.003954289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001180736,"about_ca_system_score_gemma":0.001899053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007721997,"about_ca_topic_score_gemma":0.007070976,"domain_scores_codex":[0.9970146,0.001198226,0.0002860879,0.0005191338,0.0006908004,0.0002911818],"domain_scores_gemma":[0.9856455,0.009140452,0.001017882,0.001383886,0.002214351,0.0005979704],"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":[0.0006980042,0.0001103625,0.02200522,0.002437913,0.0001755759,0.001114391,0.01980135,0.001181908,0.05311068,0.0967757,0.01736252,0.7852265],"study_design_scores_gemma":[0.0002526724,0.001001859,0.1489795,0.0020425,0.000481703,0.00628608,0.04551067,0.004197389,0.03077893,0.48445,0.2756429,0.0003759114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6008554,0.0488521,0.09635323,0.03921051,0.001270941,0.0003401889,0.002451435,0.001720208,0.208946],"genre_scores_gemma":[0.9524684,0.01025563,0.02667363,0.001337986,0.0005124694,0.0002467392,0.001580818,0.0006277029,0.006296728],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009189421,"threshold_uncertainty_score":0.03074169,"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."}}