{"id":"W1972260496","doi":"10.3115/1596324.1596340","title":"An incremental bayesian model for learning syntactic categories","year":2008,"lang":"en","type":"article","venue":"","topic":"Language Development and Disorders","field":"Psychology","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Bootstrapping (finance); Computer science; Artificial intelligence; Utterance; Natural language processing; Ambiguity; Bayesian probability; Bayesian inference; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002653998,0.0008128839,0.001101146,0.001448456,0.0005613383,0.001330019,0.003429506,0.002227644,0.003848776],"category_scores_gemma":[0.01286741,0.001117902,0.001167172,0.001208139,0.001463833,0.003518017,0.001407581,0.002933657,0.00119079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001667593,"about_ca_system_score_gemma":0.001431915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01039266,"about_ca_topic_score_gemma":0.01530928,"domain_scores_codex":[0.9989626,0.0004077635,0.00004788898,0.0002588182,0.00022465,0.0000983338],"domain_scores_gemma":[0.9948516,0.003845887,0.0002756041,0.0003212654,0.0005552716,0.0001503197],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000430963,0.0001881372,0.005502867,0.000217322,0.0001820607,0.0003350849,0.0007036849,0.6320973,0.004491404,0.1681458,0.007128887,0.1805765],"study_design_scores_gemma":[0.00002105503,0.00002729355,0.0004070186,0.00001369233,0.00002045766,0.00006857188,0.00001109869,0.9304475,0.0003688187,0.06770927,0.0008842794,0.00002096664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02491516,0.0003394505,0.9704717,0.0007805212,0.00004235667,0.00006437135,0.0004619051,0.0006886988,0.00223579],"genre_scores_gemma":[0.6462373,0.0007121621,0.3403011,0.0006916579,0.0001571616,0.0007418178,0.00191171,0.0002965584,0.008950639],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01039266,"threshold_uncertainty_score":0.02066433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03008754079335142,"score_gpt":0.3102462791563757,"score_spread":0.2801587383630243,"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."}}