{"id":"W2002373856","doi":"10.3115/1119176.1119186","title":"Semi-supervised verb class discovery using noisy features","year":2003,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Cluster analysis; Class (philosophy); Natural language processing; Set (abstract data type); Feature (linguistics); Verb; Feature selection; Task (project management); Selection (genetic algorithm); Unsupervised learning; Supervised learning; Face (sociological concept); Pattern recognition (psychology); Artificial neural network; Linguistics","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":[0.003872614,0.00113055,0.001987777,0.002921148,0.0008534632,0.001668555,0.00205397,0.001440678,0.001020907],"category_scores_gemma":[0.01593657,0.0004397507,0.001235154,0.001813209,0.001086836,0.002500502,0.001315943,0.001316534,0.0007509904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006539836,"about_ca_system_score_gemma":0.001021507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001614418,"about_ca_topic_score_gemma":0.00303308,"domain_scores_codex":[0.996777,0.001145202,0.0002622155,0.0008006947,0.0007487988,0.0002659956],"domain_scores_gemma":[0.9864927,0.008528125,0.001369475,0.001778862,0.001572857,0.0002580102],"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":[0.002634024,0.001662155,0.0539627,0.0008232535,0.0006150819,0.0008835928,0.001147941,0.1226016,0.06790795,0.008372345,0.01060301,0.7287863],"study_design_scores_gemma":[0.00009499291,0.000227494,0.01286034,0.00003889893,0.00009601701,0.0003720652,0.0002424767,0.9327455,0.03619187,0.0141365,0.002917925,0.00007599816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.323976,0.0002829713,0.669297,0.0002744146,0.00006231689,0.0003369221,0.001258415,0.002291465,0.00222034],"genre_scores_gemma":[0.7701841,0.00006386919,0.2235831,0.00008794384,0.00005180257,0.0003535132,0.00423686,0.0001592899,0.001279479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003872614,"threshold_uncertainty_score":0.02048063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01515612611375898,"score_gpt":0.2672699766217805,"score_spread":0.2521138505080215,"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."}}