{"id":"W3122399969","doi":"10.1007/s10579-020-09519-z","title":"Exploring the role of lexis and grammar for the stable identification of register in an unrestricted corpus of web documents","year":2021,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Brockhouse Institute for Materials Research; Brock University","funders":"National Science Foundation of Sri Lanka; Social Sciences and Humanities Research Council of Canada; Turun Yliopisto; Emil Aaltosen Säätiö; AGE-WELL; National Science Foundation","keywords":"Lexis; Register (sociolinguistics); Computer science; Natural language processing; Variation (astronomy); Artificial intelligence; Corpus linguistics; Identification (biology); Linguistics; Text corpus","routes":{"ca_aff":true,"ca_fund":true,"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":[0.009382294,0.0008739304,0.0008480606,0.003522418,0.001760971,0.005902129,0.001311682,0.001412116,0.00243498],"category_scores_gemma":[0.04574421,0.0007533643,0.00131153,0.002167539,0.003206459,0.009930177,0.002618184,0.003651771,0.001171437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001962395,"about_ca_system_score_gemma":0.002071826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01359849,"about_ca_topic_score_gemma":0.02087571,"domain_scores_codex":[0.9966619,0.002075292,0.0001680064,0.0007769508,0.0002063381,0.0001114537],"domain_scores_gemma":[0.9683222,0.02622248,0.001470128,0.002487725,0.001107539,0.0003898765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001468755,0.000623674,0.2460164,0.0008695507,0.0009639168,0.001304475,0.01427177,0.2193172,0.01552687,0.1178651,0.01175561,0.3700167],"study_design_scores_gemma":[0.00004172297,0.0000882754,0.01661764,0.0001138218,0.0001204338,0.0002028382,0.001393311,0.8837363,0.002129802,0.09122659,0.004254509,0.00007474152],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7490824,0.002278871,0.2282239,0.005804178,0.0001340149,0.0002114759,0.001898811,0.001328064,0.01103816],"genre_scores_gemma":[0.9544843,0.0004414921,0.04089524,0.000209798,0.00006928164,0.0001268929,0.002146523,0.000320802,0.001305709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01359849,"threshold_uncertainty_score":0.0496189,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05024759076246877,"score_gpt":0.3165752133910301,"score_spread":0.2663276226285614,"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."}}