@inproceedings{liu-etal-2025-driving,
    title = "Driving {C}hinese Spelling Correction from a Fine-Grained Perspective",
    author = "Liu, Linfeng  and
      Wu, Hongqiu  and
      Zhao, Hai",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2025.coling-main.715/",
    pages = "10727--10737",
    abstract = "This paper explores the task: Chinese spelling correction (CSC), from a fine-grained perspec- tive by recognizing that existing evaluations lack nuanced typology for the spelling errors. This deficiency can create a misleading impres- sion of model performance, incurring an {\textquotedblleft}in- visible{\textquotedblright} bottleneck hindering the advancement of CSC research. In this paper, we first cate- gorize spelling errors into six types and con- duct a fine-grained evaluation across a wide variety of models, including BERT-based mod- els and LLMs. Thus, we are able to pinpoint the underlying weaknesses of existing state-of- the-art models - utilizing contextual clues and handling co-existence of multiple typos, asso- ciated to contextual errors and multi-typo er- rors. However, these errors occur infrequently in conventional training corpus. Therefore, we introduce new error generation methods to aug- ment their occurrence, which can be leveraged to enhance the training of CSC models. We hope this work could provide fresh insight for future CSC research."
}