{"id":"W2056469463","doi":"10.3115/1072228.1072376","title":"Investigating the relationship between word segmentation performance and retrieval performance in Chinese IR","year":2002,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Segmentation; Text segmentation; Artificial intelligence; Natural language processing; Word (group theory); Information retrieval; Pattern recognition (psychology); Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004422268,0.00008410185,0.0000763931,0.00007009853,0.0001963207,0.00009397342,0.0002845202,0.00003652577,0.000007373927],"category_scores_gemma":[0.0001388533,0.00005793963,0.00001064791,0.000497167,0.00003792996,0.0008439285,0.0001166521,0.0002012758,0.00001643253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003172892,"about_ca_system_score_gemma":0.000009748864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009180834,"about_ca_topic_score_gemma":0.000006858486,"domain_scores_codex":[0.9991769,0.0000491497,0.0002242448,0.0002048259,0.0001874119,0.0001574555],"domain_scores_gemma":[0.9993396,0.0002861215,0.00005998501,0.000256783,0.00001718728,0.00004027495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[3.006391e-7,0.000002355537,0.979171,0.00001148071,8.348546e-7,1.246714e-7,0.001652302,0.000535561,0.00001752181,0.0006861138,0.00001002679,0.01791239],"study_design_scores_gemma":[0.0001087016,0.000009580194,0.5836814,0.00001599965,7.265901e-7,0.000002004462,0.00001729442,0.4156813,0.00005222958,0.000373335,0.000008637703,0.00004880778],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9775336,0.00005396321,0.01929376,0.001432251,0.00005600534,0.0001254056,1.302397e-7,0.00005913301,0.001445781],"genre_scores_gemma":[0.98048,0.00001548249,0.018884,0.0001605747,0.00005822854,0.000004603595,7.248471e-7,0.000003887132,0.0003924929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4151457,"threshold_uncertainty_score":0.236271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06429135091460345,"score_gpt":0.2687473794253539,"score_spread":0.2044560285107504,"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."}}