{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007630758,0.0005396144,0.0005521141,0.001848836,0.0006444065,0.001691605,0.0004590361,0.0008261612,0.001107147],"category_scores_gemma":[0.04714511,0.0002872709,0.0004227589,0.003507693,0.00112309,0.003296304,0.0007162805,0.0008355337,0.0007200495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000865082,"about_ca_system_score_gemma":0.0006333336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009180247,"about_ca_topic_score_gemma":0.006723566,"domain_scores_codex":[0.9969627,0.001208237,0.0003480456,0.0005852898,0.0005273358,0.000368349],"domain_scores_gemma":[0.9133372,0.07122631,0.006703774,0.00370756,0.004151911,0.0008732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002049107,0.0003945624,0.7871392,0.000596009,0.0005268434,0.0003407932,0.005055401,0.03729186,0.03708176,0.001496426,0.001519272,0.1265087],"study_design_scores_gemma":[0.00002606562,0.001090726,0.8935361,0.00001943996,0.0001924439,0.0002334119,0.001275632,0.08461834,0.01698478,0.001259482,0.0006659928,0.00009765696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9956183,0.0003639386,0.002231304,0.00008574085,0.000005337773,0.00001712057,0.0001173765,0.00008011415,0.001480699],"genre_scores_gemma":[0.9984739,0.00008381236,0.0008375364,0.00001662048,0.00001420861,0.000009722306,0.000309034,0.00002567376,0.0002294321],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009180247,"threshold_uncertainty_score":0.0403558,"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."}}