{"id":"W1586413166","doi":"10.3115/1118935.1118941","title":"Text classification in Asian languages without word segmentation","year":2003,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Text segmentation; Artificial intelligence; Natural language processing; Language model; n-gram; Word (group theory); Segmentation; Feature (linguistics); Character (mathematics); Key (lock); Word lists by frequency; Simple (philosophy); Linguistics; 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":[0.0001789973,0.0000799988,0.00007437186,0.0001903877,0.0000439871,0.0001002619,0.0003096564,0.00005697926,0.00006977552],"category_scores_gemma":[0.00006194756,0.00006986336,0.00001850996,0.0004990756,0.00002871162,0.0005248912,0.00003050026,0.00007548933,0.0001494182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005958532,"about_ca_system_score_gemma":0.00002831297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009172792,"about_ca_topic_score_gemma":0.00005453698,"domain_scores_codex":[0.9992299,0.00005088991,0.000175282,0.0002535092,0.0001422209,0.0001482037],"domain_scores_gemma":[0.9994693,0.00002325827,0.00006629037,0.0003926246,0.00002311897,0.00002545138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[9.394474e-7,0.00004495458,0.02574952,0.000002846835,0.000002122676,0.000001019747,0.0003141345,0.000002514498,0.006358578,0.7895874,0.0005354322,0.1774006],"study_design_scores_gemma":[0.001967231,0.0001244973,0.6795692,0.00004046395,0.00000805998,0.00002004324,0.01662115,0.01026478,0.1942832,0.05119971,0.0449721,0.0009296359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05588375,0.00009830817,0.7880285,0.005827494,0.0001460504,0.0003321739,3.821639e-7,0.0009798049,0.1487035],"genre_scores_gemma":[0.9187962,0.00001549902,0.07888921,0.0001281774,0.000004569163,0.00004320383,0.000002542957,0.000003892818,0.002116675],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8629125,"threshold_uncertainty_score":0.2848945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02359207191929053,"score_gpt":0.2946768134136925,"score_spread":0.2710847414944019,"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."}}