Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction

Chenming Tang, Fanyi Qu, Yunfang Wu


Abstract
In the era of large language models (LLMs), in-context learning (ICL) stands out as an effective prompting strategy that explores LLMs’ potency across various tasks. However, applying LLMs to grammatical error correction (GEC) is still a challenging task. In this paper, we propose a novel ungrammatical-syntax-based in-context example selection strategy for GEC. Specifically, we measure similarity of sentences based on their syntactic structures with diverse algorithms, and identify optimal ICL examples sharing the most similar ill-formed syntax to the test input. Additionally, we carry out a two-stage process to further improve the quality of selection results. On benchmark English GEC datasets, empirical results show that our proposed ungrammatical-syntax-based strategies outperform commonly-used word-matching or semantics-based methods with multiple LLMs. This indicates that for a syntax-oriented task like GEC, paying more attention to syntactic information can effectively boost LLMs’ performance. Our code is available at https://github.com/JamyDon/SynICL4GEC.
Anthology ID:
2024.naacl-long.99
Volume:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1758–1770
Language:
URL:
https://aclanthology.org/2024.naacl-long.99
DOI:
Bibkey:
Cite (ACL):
Chenming Tang, Fanyi Qu, and Yunfang Wu. 2024. Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1758–1770, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Ungrammatical-syntax-based In-context Example Selection for Grammatical Error Correction (Tang et al., NAACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.naacl-long.99.pdf
Copyright:
 2024.naacl-long.99.copyright.pdf