Towards Harnessing the Most of ChatGPT for Korean Grammatical Error Correction-Reference-Cited by-同舟云学术

Towards Harnessing the Most of ChatGPT for Korean Grammatical Error Correction

Published:2024-04-10 Issue:8 Volume:14 Page:3195
ISSN:2076-3417
Container-title:Applied Sciences
language:en
Short-container-title:Applied Sciences

Author:

Park Chanjun¹^ORCID,Koo Seonmin²^ORCID,Kim Gyeongmin³^ORCID,Lim Heuiseok²³^ORCID

Affiliation:

1. Upstage, 338, Gwanggyojungang-ro, Suji-gu, Yongin-si 16942, Gyeonggi-do, Republic of Korea

2. Department of Computer Science and Engineering, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea

3. Human-Inspired AI Research, 145, Anam-ro, Seongbuk-gu, Seoul 02841, Republic of Korea

Abstract

In this study, we conduct a pioneering and comprehensive examination of ChatGPT’s (GPT-3.5 Turbo) capabilities within the realm of Korean Grammatical Error Correction (K-GEC). Given the Korean language’s agglutinative nature and its rich linguistic intricacies, the task of accurately correcting errors while preserving Korean-specific sentiments is notably challenging. Utilizing a systematic categorization of Korean grammatical errors, we delve into a meticulous, case-specific analysis to identify the strengths and limitations of a ChatGPT-based correction system. We also critically assess influential parameters like temperature and specific error criteria, illuminating potential strategies to enhance ChatGPT’s efficacy in K-GEC tasks. Our findings offer valuable contributions to the expanding domain of NLP research centered on the Korean language.

Funder

National Research Foundation of Korea

Publisher

MDPI AG

Link

https://www.mdpi.com/2076-3417/14/8/3195/pdf

Reference46 articles.

1. Neural spelling correction: Translating incorrect sentences to correct sentences for multimedia;Park;Multimed. Tools Appl.,2020

2. Wang, Y., Wang, Y., Liu, J., and Liu, Z. (2020). A comprehensive survey of grammar error correction. arXiv.

3. Context-Sensitive Spelling Error Correction Techniques in Korean Documents using Generative Adversarial Network;Lee;J. Korea Multimed. Soc.,2021

4. HANSpeller: A unified framework for Chinese spelling correction;Xiong;Int. J. Comput. Linguist. Chin. Lang. Process.,2015

5. Kim, M., Jin, J., Kwon, H.C., and Yoon, A. (2013, January 3–5). Statistical context-sensitive spelling correction using typing error rate. Proceedings of the 2013 IEEE 16th International Conference on Computational Science and Engineering, Sydney, Australia.