{"id":"W4405633760","doi":"10.1109/mlnlp63328.2024.10800442","title":"Improving Chinese Punctuation Restoration via External POS Tagger","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Punctuation; Computer science; Natural language processing; Artificial intelligence; Speech recognition","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":[0.001975221,0.002309412,0.00157851,0.002920507,0.001090377,0.001111975,0.001459363,0.0008748606,0.003045209],"category_scores_gemma":[0.005703459,0.0003699667,0.001406413,0.002404189,0.0007764575,0.00233761,0.00185735,0.001321048,0.006757015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006519094,"about_ca_system_score_gemma":0.002567673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005631352,"about_ca_topic_score_gemma":0.01009893,"domain_scores_codex":[0.998317,0.0003372399,0.0002269418,0.0005746966,0.0003799712,0.0001641034],"domain_scores_gemma":[0.99695,0.0005579636,0.0002643309,0.001159354,0.0009355313,0.0001329075],"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":[0.0009496849,0.0003725091,0.008979482,0.0007584926,0.0001792417,0.0011788,0.0006076607,0.02337353,0.1033502,0.002479389,0.03544891,0.8223222],"study_design_scores_gemma":[0.0002231815,0.0007993921,0.01653234,0.0001439386,0.0005214877,0.001681784,0.001171572,0.5322854,0.3682711,0.009135841,0.06897189,0.0002620947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3019224,0.002820161,0.6212867,0.0006601863,0.001457985,0.0005170937,0.007191541,0.05580356,0.008340309],"genre_scores_gemma":[0.4923383,0.001187147,0.4634812,0.0005791718,0.000250153,0.0003070278,0.02797938,0.001828645,0.01204894],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005631352,"threshold_uncertainty_score":0.01119715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006599269837192123,"score_gpt":0.2681952532649079,"score_spread":0.2615959834277158,"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."}}