{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000188684,0.0001617841,0.0001454511,0.00009543849,0.0001261776,0.0004873638,0.0007577714,0.0001009911,0.00002114652],"category_scores_gemma":[0.00009292149,0.0001243192,0.00006533902,0.0004268287,0.00003652582,0.001407669,0.0001823819,0.0002033317,0.00001081173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007042501,"about_ca_system_score_gemma":0.00009677576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005940128,"about_ca_topic_score_gemma":0.00001246591,"domain_scores_codex":[0.9988489,0.00006582068,0.0001466665,0.0003753071,0.0002653952,0.0002979188],"domain_scores_gemma":[0.9992254,0.00005276405,0.00004896565,0.0005451317,0.00006191558,0.00006581715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009349382,0.0001078632,0.0008709152,0.00006662962,0.0000306689,0.0001102812,0.000687069,0.00005694568,0.1524994,0.8215785,0.008670032,0.01531237],"study_design_scores_gemma":[0.0005418923,0.00008154144,0.0001951691,0.000126124,0.00001858204,0.000283457,0.00009136742,0.01941172,0.8801303,0.09114092,0.007026436,0.0009525055],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01585596,0.002198404,0.9705298,0.000352476,0.0002976833,0.0001309649,0.000001106416,0.0009138664,0.009719715],"genre_scores_gemma":[0.4383681,0.000005736211,0.5591875,0.0008574604,0.0000300558,0.000002932935,8.214615e-7,0.000009830296,0.00153763],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7304376,"threshold_uncertainty_score":0.5069588,"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."}}