{"id":"W3017045910","doi":"10.1075/ivitra.24.08lho","title":"Collecting collocations from general and specialised corpora","year":2020,"lang":"en","type":"book-chapter","venue":"IVITRA research in linguistics and literature","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Natural language processing; Linguistics; Computer science; Artificial intelligence; History; 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":[0.003657703,0.000421918,0.0007643554,0.01348745,0.001980076,0.002149255,0.0009069951,0.0007415843,0.005715468],"category_scores_gemma":[0.01602173,0.0005671757,0.0004500596,0.01476784,0.001598283,0.002604331,0.003222654,0.0007785539,0.002374277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007975431,"about_ca_system_score_gemma":0.001099622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002456183,"about_ca_topic_score_gemma":0.006133986,"domain_scores_codex":[0.9955394,0.001545191,0.0007004756,0.001093703,0.0009357493,0.000185468],"domain_scores_gemma":[0.9744002,0.01349959,0.001519069,0.005853482,0.00421347,0.0005142104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007051208,0.0003056947,0.1163692,0.005614359,0.0003163007,0.004144478,0.04794496,0.003975247,0.1648636,0.01384682,0.03628148,0.6056328],"study_design_scores_gemma":[0.0001395972,0.0003666812,0.4760817,0.001233666,0.0003710453,0.007824872,0.02505036,0.01791014,0.07946604,0.01320901,0.3780414,0.0003055849],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8396538,0.002707502,0.1108217,0.0004586426,0.0001784223,0.001009324,0.02259496,0.001717766,0.02085778],"genre_scores_gemma":[0.6378834,0.001608441,0.2950268,0.0001662683,0.0001221264,0.001067465,0.05618659,0.001150258,0.006788563],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01348745,"threshold_uncertainty_score":0.01934397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06525551906718656,"score_gpt":0.3495310843412894,"score_spread":0.2842755652741029,"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."}}