[go: up one dir, main page]

ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs

Changchun Liu, Kai Zhang, Junzhe Jiang, Zirui Liu, Hanqing Tao, Min Gao, Enhong Chen


Abstract
Chinese Spelling Check (CSC) aims to identify and correct spelling errors in Chinese texts, where enhanced semantic understanding of a sentence can significantly improve correction accuracy. Recently, Large Language Models (LLMs) have demonstrated exceptional mastery of world knowledge and semantic understanding, rendering them more robust against spelling errors. However, the application of LLMs in CSC is a double-edged sword, as they tend to unnecessarily alter sentence length and modify rare but correctly used phrases. In this paper, by leveraging the capabilities of LLMs while mitigating their limitations, we propose a novel plug-and-play Alignment-and-Replacement Module ARM that enhances the performance of existing CSC models and without the need for retraining or fine-tuning. Experiment results and analysis on three benchmark datasets demonstrate the effectiveness and competitiveness of the proposed module.
Anthology ID:
2024.emnlp-main.567
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10156–10168
Language:
URL:
https://aclanthology.org/2024.emnlp-main.567
DOI:
10.18653/v1/2024.emnlp-main.567
Bibkey:
Cite (ACL):
Changchun Liu, Kai Zhang, Junzhe Jiang, Zirui Liu, Hanqing Tao, Min Gao, and Enhong Chen. 2024. ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 10156–10168, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
ARM: An Alignment-and-Replacement Module for Chinese Spelling Check Based on LLMs (Liu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.567.pdf