SE-CSC: A Novel Summarization-Enhanced Chinese Spelling Check with Phonetic and Glyph Embeddings

Wen-Chin Hsu, Yi-Cheng Chen^*, Yi-Hsuan Kuo
Department of Information Management, National Central University, Taoyuan City, Taiwan
* Corresponding Author: Yi-Cheng Chen. Email: email
(This article belongs to the Special Issue: Advances in Natural Language Processing and Large-scale AI Models)

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2026.085408

Received 11 May 2026; Accepted 31 July 2026; Published online 11 August 2026

Download PDF

Abstract

Due to the structural complexity of Chinese characters, the occurrence of homophones and visual similarity among glyphs directly increases the difficulties presented in Chinese spell checking (CSC). These factors also indicate the importance of the connection between CSC and context-dependency. In this study, a novel framework, the Summarization-Enhanced Chinese Spell Checking (abbreviated as SE-CSC) model, is proposed, which integrates phonetic and glyph embeddings to further enhance context awareness in error detection and correction. We utilize sentence-level summarization features to augment and generate an error-guided mask that can effectively detect errors and derive more precise corrections. Several comprehensive experiments conducted on real datasets demonstrated the superiority of the proposed SE-CSC compared to existing baselines, particularly in reducing miscorrections and improving accuracy. In addition, attention visualizations and case studies are provided to confirm the ability of SE-CSC for key contextual concentration, offering a structured and adaptable approach for spelling correction in linguistically complex environments.