{"id":"W40123913","doi":"","title":"AUTOMATICALLY CONSTRUCTING A LEXICON OF VERB PHRASE IDIOMATIC COMBINATIONS","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Natural language processing; Computer science; Lexicon; Artificial intelligence; Linguistics; Flexibility (engineering); Phrase; Verb; Representation (politics); Class (philosophy); Mathematics","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":[0.0001769982,0.00008181037,0.0001384937,0.0001153421,0.00005281917,0.00008154856,0.0004893363,0.0000429109,0.00001428198],"category_scores_gemma":[0.0001058289,0.00006898725,0.00003855691,0.00036758,0.00006299033,0.0003696826,0.0001316962,0.00006864766,0.00000812057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002403872,"about_ca_system_score_gemma":0.0000687571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000775615,"about_ca_topic_score_gemma":0.00000904475,"domain_scores_codex":[0.9991834,0.00003184777,0.0002865782,0.0001536872,0.0002050764,0.0001394761],"domain_scores_gemma":[0.99936,0.00008642331,0.0001263635,0.0002928332,0.0001079593,0.00002646229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[3.29244e-7,0.00005693858,0.0001715179,0.00004201507,0.000003170351,0.00000478098,0.00007150133,0.000001484689,0.01149208,0.979476,0.0001950699,0.008485066],"study_design_scores_gemma":[0.0003157604,0.0000429137,0.0002079469,0.0001006377,0.000007317828,0.00005585808,0.00004877566,0.05894776,0.1932054,0.7468905,0.00001302731,0.0001640169],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03531408,0.0001733721,0.9521343,0.0006297858,0.00005427545,0.0001179392,8.154614e-7,0.0009961171,0.01057938],"genre_scores_gemma":[0.5192731,1.442345e-7,0.4806297,0.00003733147,0.000004967806,0.000003238683,7.168864e-7,0.000002493417,0.00004827071],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.483959,"threshold_uncertainty_score":0.2813218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006476881362674912,"score_gpt":0.2463076397073131,"score_spread":0.2398307583446382,"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."}}