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

Tzu Hsuan Chou, Chun-Yi Lin, Hung-Yu Kao


Abstract
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.
Anthology ID:
2023.acl-long.356
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6460–6476
Language:
URL:
https://aclanthology.org/2023.acl-long.356
DOI:
10.18653/v1/2023.acl-long.356
Bibkey:
Cite (ACL):
Tzu Hsuan Chou, Chun-Yi Lin, and Hung-Yu Kao. 2023. Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6460–6476, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Advancing Multi-Criteria Chinese Word Segmentation Through Criterion Classification and Denoising (Chou et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.356.pdf
Video:
 https://aclanthology.org/2023.acl-long.356.mp4