RE$^2$: Improving Chinese Grammatical Error Correction via Retrieving Appropriate Examples with Explanation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909816592531456 |
|---|---|
| author | Wang, Baoxin Luo, Yumeng Wang, Yixuan Wu, Dayong Che, Wanxiang Wang, Shijin |
| author_facet | Wang, Baoxin Luo, Yumeng Wang, Yixuan Wu, Dayong Che, Wanxiang Wang, Shijin |
| contents | The primary objective of Chinese grammatical error correction (CGEC) is to detect and correct errors in Chinese sentences. Recent research shows that large language models (LLMs) have been applied to CGEC with significant results. For LLMs, selecting appropriate reference examples can help improve their performance. However, existing methods predominantly rely on text similarity for example retrieval, a strategy that frequently mismatches actual error patterns and retrieves lexically similar yet grammatically irrelevant sentences. To address this problem, we propose a method named RE$^2$, which retrieves appropriate examples with explanations of grammatical errors. Instead of using text similarity of the input sentence, we use explanations of grammatical errors to select reference examples, which are used by LLMs to improve the performance of CGEC. We conduct experiments on two CGEC datasets and create a high-quality grammatical error explanation (GEE) dataset, which is not only used in our research but also serves as a valuable resource for future studies in both CGEC and GEE. The experimental results on the two datasets indicate that our proposed method effectively improves the performance of CGEC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_26038 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RE$^2$: Improving Chinese Grammatical Error Correction via Retrieving Appropriate Examples with Explanation Wang, Baoxin Luo, Yumeng Wang, Yixuan Wu, Dayong Che, Wanxiang Wang, Shijin Computation and Language The primary objective of Chinese grammatical error correction (CGEC) is to detect and correct errors in Chinese sentences. Recent research shows that large language models (LLMs) have been applied to CGEC with significant results. For LLMs, selecting appropriate reference examples can help improve their performance. However, existing methods predominantly rely on text similarity for example retrieval, a strategy that frequently mismatches actual error patterns and retrieves lexically similar yet grammatically irrelevant sentences. To address this problem, we propose a method named RE$^2$, which retrieves appropriate examples with explanations of grammatical errors. Instead of using text similarity of the input sentence, we use explanations of grammatical errors to select reference examples, which are used by LLMs to improve the performance of CGEC. We conduct experiments on two CGEC datasets and create a high-quality grammatical error explanation (GEE) dataset, which is not only used in our research but also serves as a valuable resource for future studies in both CGEC and GEE. The experimental results on the two datasets indicate that our proposed method effectively improves the performance of CGEC. |
| title | RE$^2$: Improving Chinese Grammatical Error Correction via Retrieving Appropriate Examples with Explanation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.26038 |