Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation

Chun Lin, Ying-Jia Lin, Chia-Jen Yeh, Yi-Ting Li, Ching-Wen Yang, Hung-Yu Kao


Abstract
Recent Chinese word segmentation (CWS) models have shown competitive performance with pre-trained language models’ knowledge. However, these models tend to learn the segmentation knowledge through in-vocabulary words rather than understanding the meaning of the entire context. To address this issue, we introduce a context-aware approach that incorporates unsupervised sentence representation learning over different dropout masks into the multi-criteria training framework. We demonstrate that our approach reaches state-of-the-art (SoTA) performance on F1 scores for six of the nine CWS benchmark datasets and out-of-vocabulary (OOV) recalls for eight of nine. Further experiments discover that substantial improvements can be brought with various sentence representation objectives.
Anthology ID:
2023.findings-emnlp.850
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12756–12763
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.850
DOI:
10.18653/v1/2023.findings-emnlp.850
Bibkey:
Cite (ACL):
Chun Lin, Ying-Jia Lin, Chia-Jen Yeh, Yi-Ting Li, Ching-Wen Yang, and Hung-Yu Kao. 2023. Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12756–12763, Singapore. Association for Computational Linguistics.
Cite (Informal):
Improving Multi-Criteria Chinese Word Segmentation through Learning Sentence Representation (Lin et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.850.pdf