Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition

Yingjie Gu, Xiaoye Qu, Zhefeng Wang, Yi Zheng, Baoxing Huai, Nicholas Jing Yuan


Abstract
Recent years have witnessed the improving performance of Chinese Named Entity Recognition (NER) from proposing new frameworks or incorporating word lexicons. However, the inner composition of entity mentions in character-level Chinese NER has been rarely studied. Actually, most mentions of regular types have strong name regularity. For example, entities end with indicator words such as “公司 (company) ” or “银行 (bank)” usually belong to organization. In this paper, we propose a simple but effective method for investigating the regularity of entity spans in Chinese NER, dubbed as Regularity-Inspired reCOgnition Network (RICON). Specifically, the proposed model consists of two branches: a regularity-aware module and a regularity-agnostic module. The regularity-aware module captures the internal regularity of each span for better entity type prediction, while the regularity-agnostic module is employed to locate the boundary of entities and relieve the excessive attention to span regularity. An orthogonality space is further constructed to encourage two modules to extract different aspects of regularity features. To verify the effectiveness of our method, we conduct extensive experiments on three benchmark datasets and a practical medical dataset. The experimental results show that our RICON significantly outperforms previous state-of-the-art methods, including various lexicon-based methods.
Anthology ID:
2022.findings-naacl.143
Volume:
Findings of the Association for Computational Linguistics: NAACL 2022
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1863–1873
Language:
URL:
https://aclanthology.org/2022.findings-naacl.143
DOI:
10.18653/v1/2022.findings-naacl.143
Bibkey:
Cite (ACL):
Yingjie Gu, Xiaoye Qu, Zhefeng Wang, Yi Zheng, Baoxing Huai, and Nicholas Jing Yuan. 2022. Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1863–1873, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition (Gu et al., Findings 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.findings-naacl.143.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2022.findings-naacl.143.mp4
Data
OntoNotes 4.0OntoNotes 5.0