{"id":"W2006877875","doi":"10.1080/01690960902840279","title":"A computational model of learning semantic roles from child-directed language","year":2009,"lang":"en","type":"article","venue":"Language and Cognitive Processes","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Natural language processing; Verb; Predicate (mathematical logic); Ambiguity; Artificial intelligence; Semantic role labeling; Comprehension; Language acquisition; Semantics (computer science); Meaning (existential); Probabilistic logic; Event (particle physics); Linguistics; Psychology; Sentence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009381943,0.0001786307,0.0002358911,0.0001290551,0.0001212855,0.0001134387,0.0003066762,0.00007064106,0.000008780851],"category_scores_gemma":[0.0003791498,0.0001561208,0.000033739,0.0003966418,0.00005629525,0.000456314,0.0001032815,0.0002168192,0.000002570459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006702647,"about_ca_system_score_gemma":0.00007175696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005411126,"about_ca_topic_score_gemma":0.00002096631,"domain_scores_codex":[0.9989403,0.00004665311,0.0001980445,0.0003705038,0.0002487798,0.0001956662],"domain_scores_gemma":[0.9992003,0.0001928099,0.000152299,0.0001114688,0.0002852619,0.00005786188],"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":[0.0001692116,0.0005597688,0.001499533,0.0006740816,0.0001891256,0.0003204019,0.1163856,0.0009421442,0.03647247,0.006108017,0.00006625032,0.8366134],"study_design_scores_gemma":[0.001777259,0.0004812077,0.001683435,0.002183281,0.0001736349,0.0001354561,0.009087531,0.5350671,0.3377207,0.1105092,0.000007440798,0.001173775],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4037423,0.02811071,0.5660446,0.0002270988,0.00001072252,0.0001502829,0.00003003897,0.0008192523,0.0008649976],"genre_scores_gemma":[0.88241,0.000048447,0.1169982,0.0003889124,0.00002805545,0.000007344978,0.00005206023,0.000009087219,0.00005786301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8354396,"threshold_uncertainty_score":0.6366423,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006790039251520495,"score_gpt":0.2534377029089888,"score_spread":0.2466476636574683,"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."}}