Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models

Chong Li, Cenyuan Zhang, Xiaoqing Zheng, Xuanjing Huang


Abstract
A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one. However, CSC models may fail to correct spelling errors covered by the confusion sets, and also will encounter unseen ones. We propose a method, which continually identifies the weak spots of a model to generate more valuable training instances, and apply a task-specific pre-training strategy to enhance the model. The generated adversarial examples are gradually added to the training set. Experimental results show that such an adversarial training method combined with the pre-training strategy can improve both the generalization and robustness of multiple CSC models across three different datasets, achieving state-of-the-art performance for CSC task.
Anthology ID:
2021.acl-short.56
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
441–446
Language:
URL:
https://aclanthology.org/2021.acl-short.56
DOI:
10.18653/v1/2021.acl-short.56
Bibkey:
Cite (ACL):
Chong Li, Cenyuan Zhang, Xiaoqing Zheng, and Xuanjing Huang. 2021. Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 441–446, Online. Association for Computational Linguistics.
Cite (Informal):
Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models (Li et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-short.56.pdf
Optional supplementary material:
 2021.acl-short.56.OptionalSupplementaryMaterial.zip
Video:
 https://aclanthology.org/2021.acl-short.56.mp4
Code
 FDChongli/TwoWaysToImproveCSC