@inproceedings{koo-etal-2024-search,
title = "Search if you don{'}t know! Knowledge-Augmented {K}orean Grammatical Error Correction with Large Language Models",
author = "Koo, Seonmin and
Kim, Jinsung and
Park, Chanjun and
Lim, Heuiseok",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.6",
doi = "10.18653/v1/2024.findings-emnlp.6",
pages = "96--125",
abstract = "Grammatical error correction (GEC) system is a practical task used in the real world, showing high achievements alongside the development of large language models (LLMs). However, these achievements have been primarily obtained in English, and there is a relative lack of performance for non-English data, such as Korean. We hypothesize that this insufficiency occurs because relying solely on the parametric knowledge of LLMs makes it difficult to thoroughly understand the given context in the Korean GEC. Therefore, we propose a Knowledge-Augmented GEC (KAGEC) framework that incorporates evidential information from external sources into the prompt for the GEC task. KAGEC first extracts salient phrases from the given source and retrieves non-parametric knowledge based on these phrases, aiming to enhance the context-aware generation capabilities of LLMs. Furthermore, we conduct validations for fine-grained error types to identify those requiring a retrieval-augmented manner when LLMs perform Korean GEC. According to experimental results, most LLMs, including ChatGPT, demonstrate significant performance improvements when applying KAGEC.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koo-etal-2024-search">
<titleInfo>
<title>Search if you don’t know! Knowledge-Augmented Korean Grammatical Error Correction with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seonmin</namePart>
<namePart type="family">Koo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinsung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanjun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heuiseok</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammatical error correction (GEC) system is a practical task used in the real world, showing high achievements alongside the development of large language models (LLMs). However, these achievements have been primarily obtained in English, and there is a relative lack of performance for non-English data, such as Korean. We hypothesize that this insufficiency occurs because relying solely on the parametric knowledge of LLMs makes it difficult to thoroughly understand the given context in the Korean GEC. Therefore, we propose a Knowledge-Augmented GEC (KAGEC) framework that incorporates evidential information from external sources into the prompt for the GEC task. KAGEC first extracts salient phrases from the given source and retrieves non-parametric knowledge based on these phrases, aiming to enhance the context-aware generation capabilities of LLMs. Furthermore, we conduct validations for fine-grained error types to identify those requiring a retrieval-augmented manner when LLMs perform Korean GEC. According to experimental results, most LLMs, including ChatGPT, demonstrate significant performance improvements when applying KAGEC.</abstract>
<identifier type="citekey">koo-etal-2024-search</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.6</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.6</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>96</start>
<end>125</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Search if you don’t know! Knowledge-Augmented Korean Grammatical Error Correction with Large Language Models
%A Koo, Seonmin
%A Kim, Jinsung
%A Park, Chanjun
%A Lim, Heuiseok
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F koo-etal-2024-search
%X Grammatical error correction (GEC) system is a practical task used in the real world, showing high achievements alongside the development of large language models (LLMs). However, these achievements have been primarily obtained in English, and there is a relative lack of performance for non-English data, such as Korean. We hypothesize that this insufficiency occurs because relying solely on the parametric knowledge of LLMs makes it difficult to thoroughly understand the given context in the Korean GEC. Therefore, we propose a Knowledge-Augmented GEC (KAGEC) framework that incorporates evidential information from external sources into the prompt for the GEC task. KAGEC first extracts salient phrases from the given source and retrieves non-parametric knowledge based on these phrases, aiming to enhance the context-aware generation capabilities of LLMs. Furthermore, we conduct validations for fine-grained error types to identify those requiring a retrieval-augmented manner when LLMs perform Korean GEC. According to experimental results, most LLMs, including ChatGPT, demonstrate significant performance improvements when applying KAGEC.
%R 10.18653/v1/2024.findings-emnlp.6
%U https://aclanthology.org/2024.findings-emnlp.6
%U https://doi.org/10.18653/v1/2024.findings-emnlp.6
%P 96-125
Markdown (Informal)
[Search if you don’t know! Knowledge-Augmented Korean Grammatical Error Correction with Large Language Models](https://aclanthology.org/2024.findings-emnlp.6) (Koo et al., Findings 2024)
ACL