{"id":"W110373586","doi":"","title":"Voting between Dictionary-Based and Subword Tagging Models for Chinese Word Segmentation","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Conditional random field; Computer science; Text segmentation; Word (group theory); Artificial intelligence; Voting; Natural language processing; Segmentation; Speech recognition; Matching (statistics); Pattern recognition (psychology); Mathematics; Statistics","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":[0.003633315,0.0007612994,0.00125799,0.001074833,0.000879559,0.001229147,0.002106841,0.000821398,0.003357579],"category_scores_gemma":[0.00641841,0.0005758508,0.0009346646,0.001564771,0.0005587456,0.003832191,0.001257328,0.001061513,0.002002692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009336887,"about_ca_system_score_gemma":0.001240879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005568124,"about_ca_topic_score_gemma":0.01083258,"domain_scores_codex":[0.9976789,0.0008414167,0.0001774945,0.0007395564,0.0003686481,0.0001940339],"domain_scores_gemma":[0.9966281,0.001611343,0.00017605,0.0007722544,0.0006933609,0.0001188887],"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":[0.001428616,0.0002062917,0.006757658,0.0002934678,0.0002924459,0.0002162391,0.0006018425,0.08007137,0.02374499,0.01642295,0.00899134,0.8609729],"study_design_scores_gemma":[0.00005027298,0.0001038293,0.000888018,0.0000169867,0.00008178925,0.0000931785,0.00009103486,0.9647642,0.01742418,0.01210867,0.004331763,0.00004605852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06600429,0.0003748895,0.9238212,0.0002144037,0.0001818408,0.0001274315,0.0003087808,0.00532576,0.003641342],"genre_scores_gemma":[0.644163,0.0002498414,0.3467211,0.0002342322,0.00007466151,0.0001568809,0.001652112,0.0007200882,0.006028009],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005568124,"threshold_uncertainty_score":0.01921505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01237308647396984,"score_gpt":0.2713870272343266,"score_spread":0.2590139407603568,"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."}}