{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002779977,0.0009514667,0.001072164,0.001998696,0.0007576979,0.001824841,0.001126724,0.001349874,0.00253749],"category_scores_gemma":[0.008634915,0.0003971007,0.0009935427,0.001227401,0.0005081456,0.003523912,0.001288194,0.001885782,0.003371348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005895062,"about_ca_system_score_gemma":0.000702159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001696127,"about_ca_topic_score_gemma":0.00149,"domain_scores_codex":[0.9978879,0.0008582021,0.0001941758,0.0004919937,0.0003586017,0.0002091524],"domain_scores_gemma":[0.9956696,0.002014532,0.0005042558,0.0005490311,0.0011035,0.0001590993],"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":[0.0009607158,0.0004625991,0.01460878,0.0002435254,0.0001594941,0.0004368417,0.0004336865,0.08028121,0.03139935,0.00871316,0.01830819,0.8439925],"study_design_scores_gemma":[0.00001477679,0.00004959265,0.0014542,0.00001429879,0.00001564096,0.0001006215,0.0001011449,0.9819562,0.007065268,0.007470214,0.001736951,0.00002114156],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1309493,0.0006343074,0.8509447,0.0007211113,0.0002605013,0.0001147408,0.0007421455,0.01250812,0.003125026],"genre_scores_gemma":[0.725414,0.0002114437,0.2664039,0.0002429108,0.0001753145,0.0001346311,0.002316154,0.0003821097,0.004719548],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002779977,"threshold_uncertainty_score":0.01470208,"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."}}