{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000296507,0.0001176093,0.0001851266,0.0003552178,0.00006226968,0.0003519469,0.0006245954,0.00005895846,0.000001249998],"category_scores_gemma":[0.001310656,0.0001102311,0.00003806095,0.0003268367,0.00006410813,0.0002605135,0.0001952546,0.0002384515,3.666212e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002801862,"about_ca_system_score_gemma":0.0002132432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003320232,"about_ca_topic_score_gemma":0.0001222167,"domain_scores_codex":[0.9987379,0.0000352907,0.0005034377,0.0001538249,0.0004236632,0.0001458788],"domain_scores_gemma":[0.9978311,0.0001125912,0.0006036628,0.00009914178,0.001312598,0.00004088216],"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":[0.0000586542,0.0002805103,0.03822277,0.00002966279,0.00006356197,0.001290709,0.001218048,0.0008609506,0.01212453,0.9308323,0.00006708914,0.01495117],"study_design_scores_gemma":[0.003347461,0.0003036164,0.007860321,0.001802885,0.00009647652,0.002429892,0.0004081355,0.04231433,0.03169093,0.891643,0.01694149,0.001161462],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1276342,0.0009631068,0.8688213,0.0002258757,0.002007882,0.0001104166,0.000003488272,0.00005689439,0.0001768685],"genre_scores_gemma":[0.5658462,0.00001333358,0.4334516,0.00003295965,0.0006385467,5.493895e-7,0.000001128975,0.000006597304,0.000009073819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.438212,"threshold_uncertainty_score":0.4495095,"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."}}