{"id":"W124635070","doi":"","title":"Language identification of names with SVMs","year":2010,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Language identification; Natural language processing; Artificial intelligence; Identification (biology); Language model; Transliteration; Natural language; Support vector machine; Task (project management); Cache language model; Machine translation; Universal Networking Language; Process (computing); Character (mathematics); Comprehension approach; Programming 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013461,0.00004455242,0.00005320534,0.0000532576,0.00002045261,0.00005353071,0.0005049012,0.00003000682,0.00001611913],"category_scores_gemma":[0.00003124513,0.0000291478,0.00001203875,0.0001835876,0.00003520995,0.0003008382,0.00006108837,0.00009228352,0.000006285039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000289402,"about_ca_system_score_gemma":0.00001915497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003916265,"about_ca_topic_score_gemma":0.00003493238,"domain_scores_codex":[0.9995693,0.00000662688,0.00009660967,0.0001280183,0.0001311553,0.00006827831],"domain_scores_gemma":[0.9994515,0.00001725454,0.00007134142,0.0003707974,0.00007031376,0.00001877747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000001566298,0.00001855042,0.0003242527,0.00001235085,0.00000282777,0.000003405273,0.0006919602,1.843155e-7,0.7806021,0.167384,0.0001519073,0.05080692],"study_design_scores_gemma":[0.00004527134,0.00001971645,0.0005391165,0.000006084036,0.00000148327,0.0000129969,0.00002633525,0.00121194,0.9920492,0.005943813,0.00008290173,0.00006111703],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1557846,0.0001526023,0.8415926,0.0003654101,0.0000732652,0.00007051117,5.643852e-7,0.000483857,0.001476672],"genre_scores_gemma":[0.6120849,3.622204e-7,0.3874903,0.00003527733,0.000008204754,0.000002411386,5.074155e-7,0.000002012246,0.0003759543],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4563004,"threshold_uncertainty_score":0.1188613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004026076663038785,"score_gpt":0.2520028099435107,"score_spread":0.2479767332804719,"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."}}