Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising

Tzu Hsuan Chou, Chun Yi Lin, Hung Yu Kao

研究成果: Conference contribution

摘要

Recent research on multi-criteria Chinese word segmentation (MCCWS) mainly focuses on building complex private structures, adding more handcrafted features, or introducing complex optimization processes. In this work, we show that through a simple yet elegant input-hint-based MCCWS model, we can achieve state-of-the-art (SoTA) performances on several datasets simultaneously. We further propose a novel criterion-denoising objective that hurts slightly on F1 score but achieves SoTA recall on out-of-vocabulary words. Our result establishes a simple yet strong baseline for future MCCWS research. Source code is available at https://github.com/IKMLab/MCCWS.

原文English
主出版物標題Long Papers
發行者Association for Computational Linguistics (ACL)
頁面6460-6476
頁數17
ISBN(電子)9781959429722
出版狀態Published - 2023
事件61st Annual Meeting of the Association for Computational Linguistics, ACL 2023 - Toronto, Canada
持續時間: 2023 7月 92023 7月 14

出版系列

名字Proceedings of the Annual Meeting of the Association for Computational Linguistics
1
ISSN(列印)0736-587X

Conference

Conference61st Annual Meeting of the Association for Computational Linguistics, ACL 2023
國家/地區Canada
城市Toronto
期間23-07-0923-07-14

All Science Journal Classification (ASJC) codes

  • 電腦科學應用
  • 語言和語言學
  • 語言與語言學

指紋

深入研究「Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising」主題。共同形成了獨特的指紋。

引用此