{"id":"W1978317631","doi":"10.1108/00220410710743306","title":"Machine learning for Asian language text classification","year":2007,"lang":"en","type":"article","venue":"Journal of Documentation","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Text segmentation; Artificial intelligence; Segmentation; Natural language processing; Language model; Support vector machine; Principle of maximum entropy; Market segmentation; Naive Bayes classifier; Word (group theory); Pattern recognition (psychology); Machine learning; Mathematics","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":[0.0008624198,0.00007443019,0.0001042847,0.0002902679,0.00009999501,0.0001629009,0.0003777361,0.00005139979,0.00001989007],"category_scores_gemma":[0.0001585734,0.00006391241,0.00007403813,0.0002625326,0.00002040178,0.00117448,0.00002690223,0.0001397076,0.00001249773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009753708,"about_ca_system_score_gemma":0.00002978857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003531569,"about_ca_topic_score_gemma":0.000003864681,"domain_scores_codex":[0.999041,0.00002717109,0.0004302914,0.0001127075,0.0002485783,0.0001402444],"domain_scores_gemma":[0.9989243,0.0001115197,0.000620025,0.0001448393,0.000154067,0.00004525061],"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":[0.00004910182,0.00007238411,0.003444997,0.00001569845,0.0000279435,0.000005207279,0.002003497,0.00004271147,0.05281972,0.1012576,0.0008113688,0.8394498],"study_design_scores_gemma":[0.009529444,0.003440592,0.2228296,0.0001801264,0.0001578871,0.0003526643,0.02903269,0.04828435,0.4248059,0.07898481,0.181192,0.001209949],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02283183,0.0002435885,0.9718379,0.003328511,0.0002389043,0.0001399118,4.296693e-7,0.00009195939,0.001286899],"genre_scores_gemma":[0.9399352,0.00004267794,0.05935985,0.00007800588,0.00007796493,0.000004008242,0.000006089972,0.000005876856,0.0004903458],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9171034,"threshold_uncertainty_score":0.2606272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02066179093718157,"score_gpt":0.3197743031696622,"score_spread":0.2991125122324806,"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."}}