@inproceedings{xing-etal-2025-mkt,
    title = "{MKT}: A Multi-Stage Knowledge Transfer Framework to Mitigate Catastrophic Forgetting in Multi-Domain {C}hinese Spelling Correction",
    author = "Xing, Peng  and
      Li, Yinghui  and
      Ma, Shirong  and
      Liang, Xinnian  and
      Huang, Haojing  and
      Li, Yangning  and
      Guo, Shu-Yu  and
      Zheng, Hai-Tao  and
      Jiang, Wenhao  and
      Shen, Ying",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.30/",
    pages = "451--462",
    ISBN = "979-8-89176-333-3",
    abstract = "Chinese Spelling Correction (CSC) aims to detect and correct spelling errors in given sentences. Recently, multi-domain CSC has gradually attracted the attention of researchers because it is more practicable.In this paper, we focus on the key flaw of the CSC model when adapting to multi-domain scenarios: the tendency to forget previously acquired knowledge upon learning new domain-specific knowledge (i.e., **catastrophic forgetting**).To address this, we propose a novel model-agnostic **M**ulti-stage **K**nowledge **T**ransfer (**MKT**) framework with an evolving teacher model and dynamic distillation weights for knowledge transfer in each domain, rather than focusing solely on new domain knowledge.It deserves to be mentioned that we are the first to apply continual learning methods to the multi-domain CSC task. Experiments. prove our method{'}s effectiveness over traditional approaches, highlighting the importance of overcoming catastrophic forgetting to enhance model performance."
}