Leveraging artificial intelligence through long short-term memory approach for correcting faults in Chinese language sentences

Che Lah, Muhammad Afiq and Ab Ghani, Hadhrami and Md Saleh, Nurul Izrin (2025) Leveraging artificial intelligence through long short-term memory approach for correcting faults in Chinese language sentences. IAES International Journal of Artificial Intelligence, 14 (3). pp. 1799-1808. ISSN 2252-8938

Text 02695221220251430522745.pdf Available under License Creative Commons Attribution Share Alike. Download (517kB)

Abstract

This research focus on leveraging artificial intelligence (AI) to manage the challenges faced by non-native speakers in correcting faults and misconstructions in Chinese language sentences. Learners commonly struggle with mispronunciation, incorrect character usage, improper sentence structures, and grammatical mistakes. To tackle these issues, this study generally aims to improve and optimize AI for correcting faults in Chinese language for non-native speakers. This project employs long short-term memory (LSTM) approach based on Hanyu Shuiping Kaoshi (HSK) word ordering errors (WOE) dataset. The effectiveness of leveraging LSTM in detecting and correcting errors in Chinese language sentence have been demonstrated. LSTM shows the capability to be learn Chinese sentence structure, identify mistakes, and correct them. In summary, this research seeks to benefits the power of AI to provide innovative solutions for detecting, correcting faults and misconstructions in Chinese language sentences. This paper essentially useful for those who wish to learn how to correct their Chinese writing and enhance language proficiency among non-native speakers.

Item Type:	Article
Uncontrolled Keywords:	Artificial intelligence, Chinese sentence correction, Long short-term memory, Mandarin language education, Non-native speakers
Divisions:	Faculty of Information and Communication Technology
Depositing User:	Sabariah Ismail
Date Deposited:	18 Aug 2026 04:15
Last Modified:	18 Aug 2026 04:15
URI:	http://eprints.utem.edu.my/id/eprint/30315
Statistic Details:	View Download Statistic

Actions (login required)

View Item