{"id":"W2079754016","doi":"10.3115/1613186.1613187","title":"Statistical measures of the semi-productivity of light verb constructions","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Measure (data warehouse); Productivity; Verb; Natural language processing; Computer science; Artificial intelligence; Statistical analysis; Linguistics; Mathematics; Statistics; Data mining; Philosophy","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":[0.0001449602,0.00005508403,0.00009980986,0.00003389582,0.00004694423,0.00001411502,0.0005094518,0.00003157751,0.000006768552],"category_scores_gemma":[0.0002028937,0.00003318681,0.00003077194,0.0002879805,0.0001690827,0.0001582575,0.0001641485,0.00009651231,8.458089e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002198341,"about_ca_system_score_gemma":0.0001134054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009240864,"about_ca_topic_score_gemma":0.00002258433,"domain_scores_codex":[0.9993642,0.00003196345,0.0001383227,0.0001491728,0.0002321623,0.00008420549],"domain_scores_gemma":[0.999326,0.00003521762,0.00007548231,0.0004112123,0.0001319882,0.00002013818],"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":[0.000001996917,0.0000443594,0.0004213705,0.00002137887,0.000007808256,8.296559e-7,0.0002061463,0.00001184672,0.06811936,0.9213139,0.0002093367,0.009641617],"study_design_scores_gemma":[0.00006398268,0.00001881048,0.0006193702,0.00002270168,0.000004351996,0.00002030409,0.00001088115,0.00003871507,0.8045388,0.1945336,0.0000845818,0.00004397338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01328961,0.0002348018,0.9833122,0.001502229,0.0001463976,0.00008371665,0.000004606818,0.0001284899,0.001297879],"genre_scores_gemma":[0.6632653,0.000001005419,0.336677,0.00001958779,0.000008818866,0.00000123982,9.369939e-8,0.000001543717,0.00002550807],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7364194,"threshold_uncertainty_score":0.1353319,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.014977395325543,"score_gpt":0.2579192293006384,"score_spread":0.2429418339750954,"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."}}