Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development, ICSETPSD 2023, 17th-18th November 2023, Coimbatore, Tamilnadu, India

Research Article

Design of English Grammar Error Correction System Based on Deep Learning Algorithms

Download120 downloads
  • @INPROCEEDINGS{10.4108/eai.17-11-2023.2342643,
        author={Wei  Cao},
        title={Design of English Grammar Error Correction System Based on Deep Learning Algorithms},
        proceedings={Proceedings of the First International Conference on Science, Engineering and Technology Practices for Sustainable Development, ICSETPSD 2023, 17th-18th November 2023, Coimbatore, Tamilnadu, India},
        publisher={EAI},
        proceedings_a={ICSETPSD},
        year={2024},
        month={1},
        keywords={deep learning english grammar error correction system sequence model},
        doi={10.4108/eai.17-11-2023.2342643}
    }
    
  • Wei Cao
    Year: 2024
    Design of English Grammar Error Correction System Based on Deep Learning Algorithms
    ICSETPSD
    EAI
    DOI: 10.4108/eai.17-11-2023.2342643
Wei Cao1,*
  • 1: Sichuan University of Media and Communications, Chengdu, Sichuan Province, China
*Contact email: caowei66@21cn.com

Abstract

With the popularity of the Internet, English has become a globally used language, and English grammar(EG) errors have become a universal problem worldwide. EG errors not only affect daily communication but also cause reading and writing mistakes. Traditional grammar analysis methods mainly look for EG errors through static analysis, but this method can only detect some fixed types of grammar errors and cannot provide real-time EG correction. Based on this, this paper proposes an EG correction system based on deep learning(DL) algorithms. Through this system, it is hoped to provide more accurate and real-time EG error detection services. According to the experimental results of the system, it can be concluded that the grammar error recognition accuracy of the sequence model is the highest, reaching 82.2%, but its recall rate is slightly lower, only 42.3%. The accuracy of the grammar correction system based on DL can be further improved. The design, implementation, and testing processes of the system provide valuable references for the practical application of DL technologies in natural language processing tasks, such as grammar error detection and correction.