{"id":"W2802325800","doi":"10.1108/lht-12-2017-0271","title":"Corpus linguistics is not just for linguists","year":2018,"lang":"en","type":"article","venue":"Library Hi Tech","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Corpus linguistics; Computer science; Applied linguistics; Computational linguistics; Field (mathematics); Quantitative linguistics; Text linguistics; Text corpus; Linguistics; Natural language processing; Artificial intelligence; Value (mathematics); Data science","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":[0.05580889,0.0009768044,0.002050596,0.009259458,0.01048313,0.02132918,0.003478728,0.004539399,0.01750417],"category_scores_gemma":[0.1435739,0.001131242,0.0008999488,0.009462493,0.02737289,0.03469522,0.01053644,0.01409747,0.006252019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006693121,"about_ca_system_score_gemma":0.01287955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003530277,"about_ca_topic_score_gemma":0.004156583,"domain_scores_codex":[0.9331446,0.05097947,0.003292728,0.004170505,0.007692667,0.0007201246],"domain_scores_gemma":[0.7461881,0.1895571,0.007540253,0.03034567,0.02212474,0.004244201],"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":[0.00005491614,0.00004152862,0.001043781,0.001356849,0.00007392249,0.0002051007,0.01882464,0.0004992858,0.0005707144,0.756049,0.134461,0.08681925],"study_design_scores_gemma":[0.00001689828,0.00002413405,0.0002636609,0.002841534,0.00002421356,0.0002726071,0.007341773,0.0006056573,0.0003496603,0.2361231,0.7520967,0.00004006433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.007322162,0.04239262,0.239643,0.5508641,0.02719706,0.001019806,0.001703496,0.001794304,0.1280634],"genre_scores_gemma":[0.2736684,0.05294627,0.4213085,0.1348993,0.03413493,0.005846121,0.002793302,0.00570688,0.06869625],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05580889,"threshold_uncertainty_score":0.2951491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02508153720078917,"score_gpt":0.2969873667420595,"score_spread":0.2719058295412703,"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."}}