{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001065011,0.0001821286,0.0001751925,0.0001392762,0.0001914036,0.0003130059,0.001628901,0.0001591071,0.00003401626],"category_scores_gemma":[0.0005391834,0.0001651251,0.00007328817,0.0004503114,0.0001026105,0.0003745429,0.0005359928,0.0001840601,0.00005384014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001556476,"about_ca_system_score_gemma":0.0001104525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006494028,"about_ca_topic_score_gemma":5.442062e-7,"domain_scores_codex":[0.9987263,0.0000162058,0.0002395953,0.0004710203,0.0002018527,0.0003450352],"domain_scores_gemma":[0.9987274,0.0001119054,0.000121373,0.0007427083,0.0002017065,0.0000949343],"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":[0.00005621016,0.0000987814,0.0005481179,0.0001782226,0.00002388255,0.00005907144,0.00113729,1.079449e-7,0.004075906,0.6378565,0.2536543,0.1023116],"study_design_scores_gemma":[0.0001472494,0.0001807525,0.00002517148,0.00006125576,0.000006155597,0.00000976723,0.000003062198,0.003121532,0.4689004,0.1201389,0.4071478,0.0002579276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001572644,0.002725138,0.9538469,0.005021653,0.003927862,0.0008334917,0.00008105634,0.009038839,0.02295244],"genre_scores_gemma":[0.2235026,0.00001235344,0.7674085,0.004679436,0.001562357,0.00002347285,0.000009254127,0.00003187737,0.002770141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5177177,"threshold_uncertainty_score":0.6733607,"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."}}