{"id":"W2048359833","doi":"10.1007/s10579-007-9017-9","title":"Automatically learning semantic knowledge about multiword predicates","year":2007,"lang":"en","type":"article","venue":"Computers and the Humanities","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Noun; Natural language processing; Linguistics; Artificial intelligence; Focus (optics); Verb","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":[0.000828934,0.0001448599,0.0001850682,0.0001072337,0.0005843299,0.0006511289,0.0007752857,0.00004753865,0.000003303371],"category_scores_gemma":[0.00006287135,0.00009233788,0.0000495679,0.0001223465,0.0005268346,0.0002666725,0.0005368313,0.0002568139,0.000009248053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001740321,"about_ca_system_score_gemma":0.00002248674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002438217,"about_ca_topic_score_gemma":0.0000154397,"domain_scores_codex":[0.9990626,0.00008214391,0.0002203316,0.0002220826,0.0001480972,0.0002647564],"domain_scores_gemma":[0.9989457,0.0006098007,0.00009042627,0.000242941,0.000074588,0.00003661721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001133472,0.0000252945,0.00009519665,0.00008919935,0.00002563338,0.00001657774,0.01381863,0.000004043723,0.00003919316,0.8761606,0.0004496223,0.1092647],"study_design_scores_gemma":[0.002291155,0.0002618595,0.003133907,0.000832236,0.00005264698,0.0002076434,0.0007269999,0.6557445,0.00214893,0.3106027,0.02313662,0.0008608369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007485312,0.009402706,0.9784904,0.0002872816,0.000264639,0.0001618519,1.851198e-7,0.001043558,0.002864035],"genre_scores_gemma":[0.8347608,0.00004512222,0.1637531,0.0004306211,0.0001377496,0.000006469691,0.000001020558,0.00001079778,0.0008542712],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8272755,"threshold_uncertainty_score":0.627885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01257919200372212,"score_gpt":0.2518575762560514,"score_spread":0.2392783842523293,"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."}}