{"id":"W2759906493","doi":"10.18653/v1/w17-5023","title":"Ensemble Methods for Native Language Identification","year":2017,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Identification (biology); Natural language processing; Artificial intelligence; Language identification; Natural language","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":[0.005203999,0.00135817,0.001932585,0.003457829,0.00102191,0.001616297,0.001674567,0.001207844,0.002390401],"category_scores_gemma":[0.01253899,0.0005084923,0.001396295,0.002005809,0.0004221928,0.002959093,0.002033842,0.002220076,0.001881943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005189281,"about_ca_system_score_gemma":0.0008476377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003835053,"about_ca_topic_score_gemma":0.005709629,"domain_scores_codex":[0.9972234,0.001068412,0.0001632084,0.0006783461,0.0006511685,0.0002154477],"domain_scores_gemma":[0.9924465,0.003474335,0.0003708434,0.001705443,0.001790974,0.0002119467],"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":[0.0001981697,0.0001727366,0.01103044,0.0001289286,0.0006388563,0.0001023206,0.0002722052,0.1628519,0.002862212,0.00692007,0.01089358,0.8039286],"study_design_scores_gemma":[0.000007609819,0.00005420182,0.001564214,0.00002463443,0.00005494087,0.00007225906,0.00006484801,0.9815965,0.001631106,0.01210285,0.002805427,0.00002145377],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02954389,0.002310721,0.9615418,0.0003309799,0.0002897759,0.00007635317,0.0004640217,0.002568357,0.002874176],"genre_scores_gemma":[0.6400629,0.001446365,0.344513,0.0003398707,0.0007154959,0.0002976942,0.003258895,0.0006285397,0.008737436],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005203999,"threshold_uncertainty_score":0.02752167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0906035831245341,"score_gpt":0.4595583548269149,"score_spread":0.3689547717023808,"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."}}