{"id":"W1993536130","doi":"10.1145/564376.564438","title":"Using self-supervised word segmentation in Chinese information retrieval","year":2002,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":12,"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001403767,0.0000621007,0.00006122061,0.0001299424,0.00003661256,0.0001114988,0.0002054415,0.00003238043,0.00006916993],"category_scores_gemma":[0.00001659464,0.00005494533,0.00001666484,0.0004449707,0.000003046831,0.002180487,0.00006739789,0.00005877416,0.00005220967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007706208,"about_ca_system_score_gemma":0.0000102874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003638444,"about_ca_topic_score_gemma":0.000006360302,"domain_scores_codex":[0.9993669,0.00001880054,0.0002102949,0.0001034541,0.0001783932,0.0001221095],"domain_scores_gemma":[0.9996926,0.00001418775,0.00003726205,0.0001978515,0.00002919319,0.000028876],"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":[0.00002329236,0.0002862079,0.07392159,0.0001339623,0.00003054613,0.00001885749,0.06226201,0.06862333,0.007777188,0.01888628,0.0002713812,0.7677653],"study_design_scores_gemma":[0.000322449,0.000005998953,0.002149591,0.000004631204,6.766435e-7,0.000003676022,0.00003701107,0.9968332,0.0002324869,0.0003095826,0.00003190627,0.00006876323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4595296,0.000009162318,0.5380254,0.0001581592,0.0001076259,0.00008221512,1.048529e-7,0.0001006238,0.001987066],"genre_scores_gemma":[0.6911007,0.000004015674,0.3086076,0.0002391406,0.00001882802,8.559815e-7,6.207537e-7,0.000001479145,0.00002671076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9282099,"threshold_uncertainty_score":0.2240606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03339622337105059,"score_gpt":0.2628235046659737,"score_spread":0.2294272812949231,"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."}}