Abstract
In this paper, we study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model. Through empirical analysis, we find that fine-tuning BERT tends to over-fit the error model while under-fit the language model, resulting in poor generalization to out-of-distribution error patterns. Given that BERT is the backbone of most CSC models, this phenomenon has a significant negative impact. To address this issue, we are releasing a multi-domain benchmark LEMON, with higher quality and diversity than existing benchmarks, to allow a comprehensive assessment of the open domain generalization of CSC models. Then, we demonstrate that a very simple strategy – randomly masking 20% non-error tokens from the input sequence during fine-tuning – is sufficient for learning a much better language model without sacrificing the error model. This technique can be applied to any model architecture and achieves new state-of-the-art results on SIGHAN, ECSpell, and LEMON.- Anthology ID:
- 2023.acl-long.600
- 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:
- 10743–10756
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2023.acl-long.600/
- DOI:
- 10.18653/v1/2023.acl-long.600
- Cite (ACL):
- Hongqiu Wu, Shaohua Zhang, Yuchen Zhang, and Hai Zhao. 2023. Rethinking Masked Language Modeling for Chinese Spelling Correction. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10743–10756, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Rethinking Masked Language Modeling for Chinese Spelling Correction (Wu et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2023.acl-long.600.pdf