A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check

Haojing Huang, Jingheng Ye, Qingyu Zhou, Yinghui Li, Yangning Li, Feng Zhou, Hai-Tao Zheng


Abstract
In recent years, Chinese Spelling Check (CSC) has been greatly improved by designing task-specific pre-training methods or introducing auxiliary tasks, which mostly solve this task in an end-to-end fashion. In this paper, we propose to decompose the CSC workflow into detection, reasoning, and searching subtasks so that the rich external knowledge about the Chinese language can be leveraged more directly and efficiently. Specifically, we design a plug-and-play detection-and-reasoning module that is compatible with existing SOTA non-autoregressive CSC models to further boost their performance. We find that the detection-and-reasoning module trained for one model can also benefit other models. We also study the primary interpretability provided by the task decomposition. Extensive experiments and detailed analyses demonstrate the effectiveness and competitiveness of the proposed module.
Anthology ID:
2023.findings-emnlp.771
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11514–11525
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.771
DOI:
10.18653/v1/2023.findings-emnlp.771
Bibkey:
Cite (ACL):
Haojing Huang, Jingheng Ye, Qingyu Zhou, Yinghui Li, Yangning Li, Feng Zhou, and Hai-Tao Zheng. 2023. A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 11514–11525, Singapore. Association for Computational Linguistics.
Cite (Informal):
A Frustratingly Easy Plug-and-Play Detection-and-Reasoning Module for Chinese Spelling Check (Huang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.771.pdf