{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000644347,0.0008699421,0.000695827,0.002129838,0.0007928103,0.001081589,0.0006515451,0.0006578367,0.002544974],"category_scores_gemma":[0.001999168,0.0001981988,0.0008201497,0.002126963,0.0003478452,0.001772937,0.000721372,0.0005608591,0.002446208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003494449,"about_ca_system_score_gemma":0.0008471343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002543521,"about_ca_topic_score_gemma":0.006312219,"domain_scores_codex":[0.999467,0.0001098192,0.00006783788,0.0001375969,0.0001582447,0.00005963389],"domain_scores_gemma":[0.9986501,0.0003737377,0.000169541,0.0002475239,0.000476374,0.00008267027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003661027,0.0003388096,0.01259771,0.0003420381,0.0001695308,0.0003694402,0.0006331161,0.01162648,0.1224418,0.004964353,0.007673885,0.8384768],"study_design_scores_gemma":[0.00007017403,0.0005493285,0.02092507,0.0000634908,0.0002906357,0.001016431,0.001027859,0.775539,0.1587322,0.01542877,0.02621811,0.0001388488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1754274,0.0006635594,0.8086016,0.0004115114,0.0001761542,0.0003496536,0.001255684,0.005490781,0.007623725],"genre_scores_gemma":[0.5110043,0.0003151391,0.476091,0.0002240894,0.0001557871,0.0002749219,0.002820223,0.0003064341,0.008808168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002544974,"threshold_uncertainty_score":0.008513749,"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."}}