@inproceedings{song-etal-2024-gee,
title = "{GEE}! Grammar Error Explanation with Large Language Models",
author = "Song, Yixiao and
Krishna, Kalpesh and
Bhatt, Rajesh and
Gimpel, Kevin and
Iyyer, Mohit",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.49",
doi = "10.18653/v1/2024.findings-naacl.49",
pages = "754--781",
abstract = "Existing grammatical error correction tools do not provide natural language explanations of the errors that they correct in user-written text. However, such explanations are essential for helping users learn the language by gaining a deeper understanding of its grammatical rules (DeKeyser, 2003; Ellis et al., 2006).To address this gap, we propose the task of grammar error explanation, where a system needs to provide one-sentence explanations for each grammatical error in a pair of erroneous and corrected sentences. The task is not easily solved by prompting LLMs: we find that, using one-shot prompting, GPT-4 only explains 40.6{\%} of the errors and does not even attempt to explain 39.8{\%} of the errors.Since LLMs struggle to identify grammar errors, we develop a two-step pipeline that leverages fine-tuned and prompted large language models to perform structured atomic token edit extraction, followed by prompting GPT-4 to explain each edit. We evaluate our pipeline on German, Chinese, and English grammar error correction data. Our atomic edit extraction achieves an F1 of 0.93 on German, 0.91 on Chinese, and 0.891 on English. Human evaluation of generated explanations reveals that 93.9{\%} of German errors, 96.4{\%} of Chinese errors, and 92.20{\%} of English errors are correctly detected and explained. To encourage further research, we open-source our data and code.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2024-gee">
<titleInfo>
<title>GEE! Grammar Error Explanation with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yixiao</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalpesh</namePart>
<namePart type="family">Krishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajesh</namePart>
<namePart type="family">Bhatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Gimpel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Iyyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing grammatical error correction tools do not provide natural language explanations of the errors that they correct in user-written text. However, such explanations are essential for helping users learn the language by gaining a deeper understanding of its grammatical rules (DeKeyser, 2003; Ellis et al., 2006).To address this gap, we propose the task of grammar error explanation, where a system needs to provide one-sentence explanations for each grammatical error in a pair of erroneous and corrected sentences. The task is not easily solved by prompting LLMs: we find that, using one-shot prompting, GPT-4 only explains 40.6% of the errors and does not even attempt to explain 39.8% of the errors.Since LLMs struggle to identify grammar errors, we develop a two-step pipeline that leverages fine-tuned and prompted large language models to perform structured atomic token edit extraction, followed by prompting GPT-4 to explain each edit. We evaluate our pipeline on German, Chinese, and English grammar error correction data. Our atomic edit extraction achieves an F1 of 0.93 on German, 0.91 on Chinese, and 0.891 on English. Human evaluation of generated explanations reveals that 93.9% of German errors, 96.4% of Chinese errors, and 92.20% of English errors are correctly detected and explained. To encourage further research, we open-source our data and code.</abstract>
<identifier type="citekey">song-etal-2024-gee</identifier>
<identifier type="doi">10.18653/v1/2024.findings-naacl.49</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.49</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>754</start>
<end>781</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GEE! Grammar Error Explanation with Large Language Models
%A Song, Yixiao
%A Krishna, Kalpesh
%A Bhatt, Rajesh
%A Gimpel, Kevin
%A Iyyer, Mohit
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F song-etal-2024-gee
%X Existing grammatical error correction tools do not provide natural language explanations of the errors that they correct in user-written text. However, such explanations are essential for helping users learn the language by gaining a deeper understanding of its grammatical rules (DeKeyser, 2003; Ellis et al., 2006).To address this gap, we propose the task of grammar error explanation, where a system needs to provide one-sentence explanations for each grammatical error in a pair of erroneous and corrected sentences. The task is not easily solved by prompting LLMs: we find that, using one-shot prompting, GPT-4 only explains 40.6% of the errors and does not even attempt to explain 39.8% of the errors.Since LLMs struggle to identify grammar errors, we develop a two-step pipeline that leverages fine-tuned and prompted large language models to perform structured atomic token edit extraction, followed by prompting GPT-4 to explain each edit. We evaluate our pipeline on German, Chinese, and English grammar error correction data. Our atomic edit extraction achieves an F1 of 0.93 on German, 0.91 on Chinese, and 0.891 on English. Human evaluation of generated explanations reveals that 93.9% of German errors, 96.4% of Chinese errors, and 92.20% of English errors are correctly detected and explained. To encourage further research, we open-source our data and code.
%R 10.18653/v1/2024.findings-naacl.49
%U https://aclanthology.org/2024.findings-naacl.49
%U https://doi.org/10.18653/v1/2024.findings-naacl.49
%P 754-781
Markdown (Informal)
[GEE! Grammar Error Explanation with Large Language Models](https://aclanthology.org/2024.findings-naacl.49) (Song et al., Findings 2024)
ACL
- Yixiao Song, Kalpesh Krishna, Rajesh Bhatt, Kevin Gimpel, and Mohit Iyyer. 2024. GEE! Grammar Error Explanation with Large Language Models. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 754–781, Mexico City, Mexico. Association for Computational Linguistics.