@inproceedings{xiao-etal-2024-chinese,
title = "{C}hinese Grammatical Error Correction via Large Language Model Guided Optimization Training",
author = "Xiao, Liu and
Ying, Li and
Zhengtao, Yu",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.105/",
pages = "1366--1380",
language = "eng",
abstract = "{\textquotedblleft}Pre-trained language model-based methods for Chinese Grammatical Error Correction (CGEC)are categorized into Seq2Seq and Seq2Edit types. However, both Seq2Seq and Seq2Edit mod-els depend on high-quality training data significantly. Considering the strong generation andinference ability of large language models (LLMs), we propose a large language model-guidedoptimization training method to exploit LLMs to extract error knowledge to optimize the tradi-tional CGEC model training process. On the one hand, we use error types and confusion sets asextra knowledge to guide LLMs to generate diverse pseudo data, thus extending the error distri-bution of our training data. On the other hand, LLMs are utilized to infer the predicted resultsfrom our CGEC models and obtain the re-training data, thus iteratively optimizing our pre-trainedCGEC models. Experiments on two benchmark datasets show that our LLMs-guided optimiza-tion method with small-scale training data can achieve comparable results with baseline modelswith large-scale training data. Detailed comparison experiments demonstrate that both the earlydeviser pseudo data and the later re-training data are extremely useful for traditional CGEC modeloptimization training, and can benefit from each other. We will release our code and prompts athttps://github.com/SakuraAcedia/llm-cgec-got to facilitate future work.{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-etal-2024-chinese">
<titleInfo>
<title>Chinese Grammatical Error Correction via Large Language Model Guided Optimization Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Ying</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhengtao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Pre-trained language model-based methods for Chinese Grammatical Error Correction (CGEC)are categorized into Seq2Seq and Seq2Edit types. However, both Seq2Seq and Seq2Edit mod-els depend on high-quality training data significantly. Considering the strong generation andinference ability of large language models (LLMs), we propose a large language model-guidedoptimization training method to exploit LLMs to extract error knowledge to optimize the tradi-tional CGEC model training process. On the one hand, we use error types and confusion sets asextra knowledge to guide LLMs to generate diverse pseudo data, thus extending the error distri-bution of our training data. On the other hand, LLMs are utilized to infer the predicted resultsfrom our CGEC models and obtain the re-training data, thus iteratively optimizing our pre-trainedCGEC models. Experiments on two benchmark datasets show that our LLMs-guided optimiza-tion method with small-scale training data can achieve comparable results with baseline modelswith large-scale training data. Detailed comparison experiments demonstrate that both the earlydeviser pseudo data and the later re-training data are extremely useful for traditional CGEC modeloptimization training, and can benefit from each other. We will release our code and prompts athttps://github.com/SakuraAcedia/llm-cgec-got to facilitate future work.”</abstract>
<identifier type="citekey">xiao-etal-2024-chinese</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.105/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>1366</start>
<end>1380</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chinese Grammatical Error Correction via Large Language Model Guided Optimization Training
%A Xiao, Liu
%A Ying, Li
%A Zhengtao, Yu
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G eng
%F xiao-etal-2024-chinese
%X “Pre-trained language model-based methods for Chinese Grammatical Error Correction (CGEC)are categorized into Seq2Seq and Seq2Edit types. However, both Seq2Seq and Seq2Edit mod-els depend on high-quality training data significantly. Considering the strong generation andinference ability of large language models (LLMs), we propose a large language model-guidedoptimization training method to exploit LLMs to extract error knowledge to optimize the tradi-tional CGEC model training process. On the one hand, we use error types and confusion sets asextra knowledge to guide LLMs to generate diverse pseudo data, thus extending the error distri-bution of our training data. On the other hand, LLMs are utilized to infer the predicted resultsfrom our CGEC models and obtain the re-training data, thus iteratively optimizing our pre-trainedCGEC models. Experiments on two benchmark datasets show that our LLMs-guided optimiza-tion method with small-scale training data can achieve comparable results with baseline modelswith large-scale training data. Detailed comparison experiments demonstrate that both the earlydeviser pseudo data and the later re-training data are extremely useful for traditional CGEC modeloptimization training, and can benefit from each other. We will release our code and prompts athttps://github.com/SakuraAcedia/llm-cgec-got to facilitate future work.”
%U https://aclanthology.org/2024.ccl-1.105/
%P 1366-1380
Markdown (Informal)
[Chinese Grammatical Error Correction via Large Language Model Guided Optimization Training](https://aclanthology.org/2024.ccl-1.105/) (Xiao et al., CCL 2024)
ACL