{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009462885,0.00004665173,0.00008821138,0.00005464674,0.00004463776,0.00005491912,0.0001855358,0.00002064361,0.00000134718],"category_scores_gemma":[0.0001737624,0.0000294112,0.0000155272,0.000254337,0.00004024344,0.0002992277,0.0000748471,0.00004058191,2.240738e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001040601,"about_ca_system_score_gemma":0.00002773855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002895359,"about_ca_topic_score_gemma":0.0001374528,"domain_scores_codex":[0.9992399,0.0001178923,0.000215518,0.0001335484,0.0002265391,0.00006657093],"domain_scores_gemma":[0.9991825,0.0001627846,0.0002049885,0.0002654971,0.0001734958,0.00001077344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003621254,0.00004134648,0.003588436,0.000122768,0.00001590929,6.566165e-7,0.02363049,0.0001059782,0.2907482,0.002964168,0.00000497948,0.6787408],"study_design_scores_gemma":[0.0008316711,0.0001511652,0.03564951,0.0002112801,0.00008356016,0.000007637528,0.008954267,0.2883899,0.6504436,0.01475689,0.0003761911,0.000144288],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9805016,0.01437431,0.004705509,0.0001153208,0.00002206914,0.0002429981,0.000004142602,0.00001203524,0.0000220365],"genre_scores_gemma":[0.9942515,0.000165795,0.005491809,0.00000873835,0.00001312855,0.00003837658,0.000006364195,0.000003311997,0.00002094576],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6785965,"threshold_uncertainty_score":0.1199354,"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."}}