{"id":"W2070354752","doi":"10.1075/ijcl.11.2.04cla","title":"Discovering and organizing noun-verb collocations in specialized corpora using inductive logic programming","year":2006,"lang":"en","type":"article","venue":"International Journal of Corpus Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Realization (probability); Natural language processing; Computer science; Noun; Artificial intelligence; Verb; Inductive logic programming; Relevance (law); Meaning (existential); Linguistics; Parsing; Mathematics; Psychology; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004415434,0.001297914,0.001203994,0.01149689,0.002152381,0.003580884,0.002249573,0.000922631,0.003084641],"category_scores_gemma":[0.01785681,0.001202661,0.001570262,0.009586083,0.00188178,0.004913494,0.002792645,0.001522542,0.001427429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001525389,"about_ca_system_score_gemma":0.0024337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004254276,"about_ca_topic_score_gemma":0.008355218,"domain_scores_codex":[0.9950076,0.001772691,0.0005298585,0.00151084,0.0009851452,0.0001938452],"domain_scores_gemma":[0.9857082,0.01050051,0.001267628,0.001407783,0.0009452682,0.0001705703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003664308,0.0004976615,0.02068061,0.002217477,0.0003470303,0.001907884,0.008371279,0.03136775,0.04349623,0.04258265,0.006236067,0.841929],"study_design_scores_gemma":[0.0002907182,0.0003412408,0.02621224,0.0006678398,0.0005401587,0.002401119,0.01073497,0.5967076,0.06047113,0.2069234,0.0943717,0.0003378723],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06067627,0.0004644626,0.9307573,0.000292106,0.00003204104,0.0005263148,0.00167083,0.00251236,0.003068261],"genre_scores_gemma":[0.1070048,0.0002854375,0.8864659,0.00005797893,0.00002681533,0.0005615549,0.004532794,0.0003290286,0.0007356994],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01149689,"threshold_uncertainty_score":0.02335137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02060452257872276,"score_gpt":0.3012674591553245,"score_spread":0.2806629365766018,"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."}}