Abstract
Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings. On the contrary, humans can easily infer the corresponding correct words from their misspellings and surrounding context. Inspired by this, we address the stand-alone spelling correction problem, which only corrects the spelling of each token without additional token insertion or deletion, by utilizing both spelling information and global context representations. We present a simple yet powerful solution that jointly detects and corrects misspellings as a sequence labeling task by fine-turning a pre-trained language model. Our solution outperform the previous state-of-the-art result by 12.8% absolute F0.5 score.- Anthology ID:
- 2020.findings-emnlp.37
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 407–414
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.37
- DOI:
- 10.18653/v1/2020.findings-emnlp.37
- Cite (ACL):
- Xiangci Li, Hairong Liu, and Liang Huang. 2020. Context-aware Stand-alone Neural Spelling Correction. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 407–414, Online. Association for Computational Linguistics.
- Cite (Informal):
- Context-aware Stand-alone Neural Spelling Correction (Li et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.findings-emnlp.37.pdf
- Code
- jacklxc/StandAloneSpellingCorrection