{"id":"W4245584151","doi":"10.1145/564437.564438","title":"Using self-supervised word segmentation in Chinese information retrieval","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR '02","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Character (mathematics); Word (group theory); Text segmentation; Natural language processing; Segmentation; Pattern recognition (psychology)","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":[0.000742442,0.0005760824,0.0007279543,0.002303974,0.0007352203,0.000659795,0.0008049821,0.0005158972,0.001412224],"category_scores_gemma":[0.002213288,0.0003338175,0.0006663745,0.002150296,0.0008875207,0.001907928,0.0006458154,0.0003965546,0.001178014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005862002,"about_ca_system_score_gemma":0.001340362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005379335,"about_ca_topic_score_gemma":0.007238353,"domain_scores_codex":[0.9989595,0.0002592317,0.0001173986,0.0002724464,0.0003073914,0.00008395955],"domain_scores_gemma":[0.9986678,0.0003863233,0.0001625468,0.0002460369,0.0004861254,0.00005126043],"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":[0.0002507588,0.000196805,0.002881498,0.000376002,0.0000892789,0.0001837544,0.0005113674,0.02440861,0.08847351,0.006318054,0.004908329,0.8714019],"study_design_scores_gemma":[0.00008865576,0.0003773827,0.005164707,0.00002739785,0.0001364163,0.0004090427,0.0001813891,0.8679389,0.1060667,0.008310353,0.01119868,0.0001003429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1116819,0.001114779,0.8772833,0.0002018077,0.0001014846,0.0003405786,0.000153159,0.004330184,0.004792782],"genre_scores_gemma":[0.5077643,0.0005716217,0.4838929,0.000218637,0.0001898641,0.0003937772,0.0009361787,0.0003561958,0.005676543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005379335,"threshold_uncertainty_score":0.01069605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08421405815381645,"score_gpt":0.335416479760529,"score_spread":0.2512024216067126,"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."}}