The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking
Yinghui Li, Qingyu Zhou, Yangning Li, Zhongli Li, Ruiyang Liu, Rongyi Sun, Zizhen Wang, Chao Li, Yunbo Cao, Hai-Tao Zheng
Abstract
Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors, which are mainly caused by the phonological or visual similarity. Recently, pre-trained language models (PLMs) promote the progress of CSC task. However, there exists a gap between the learned knowledge of PLMs and the goal of CSC task. PLMs focus on the semantics in text and tend to correct the erroneous characters to semantically proper or commonly used ones, but these aren’t the ground-truth corrections. To address this issue, we propose an Error-driven COntrastive Probability Optimization (ECOPO) framework for CSC task. ECOPO refines the knowledge representations of PLMs, and guides the model to avoid predicting these common characters through an error-driven way. Particularly, ECOPO is model-agnostic and it can be combined with existing CSC methods to achieve better performance. Extensive experiments and detailed analyses on SIGHAN datasets demonstrate that ECOPO is simple yet effective.- Anthology ID:
- 2022.findings-acl.252
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2022
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Editors:
- Smaranda Muresan, Preslav Nakov, Aline Villavicencio
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3202–3213
- Language:
- URL:
- https://aclanthology.org/2022.findings-acl.252
- DOI:
- 10.18653/v1/2022.findings-acl.252
- Cite (ACL):
- Yinghui Li, Qingyu Zhou, Yangning Li, Zhongli Li, Ruiyang Liu, Rongyi Sun, Zizhen Wang, Chao Li, Yunbo Cao, and Hai-Tao Zheng. 2022. The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking. In Findings of the Association for Computational Linguistics: ACL 2022, pages 3202–3213, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking (Li et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2022.findings-acl.252.pdf