@inproceedings{wei-etal-2024-training,
    title = "Training a Better {C}hinese Spelling Correction Model via Prior-knowledge Guided Teacher",
    author = "Wei, Chi  and
      Huang, Shaobin  and
      Li, Rongsheng  and
      Yan, Naiyu  and
      Wang, Rui",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-acl.806/",
    doi = "10.18653/v1/2024.findings-acl.806",
    pages = "13578--13589",
    abstract = "Recent advancements in Chinese Spelling Correction (CSC) predominantly leverage pre-trained language models (PLMs). However, a notable challenge with fine-tuned PLM-based CSC models is their tendency to over-correct, leading to poor generalization for error patterns outside the standard distribution. To address this, we developed a teacher network guided by prior knowledge for distillation learning of CSC models. Unlike traditional teacher networks, which depend on task-related pre-training, our method infuses task-related prior information into the teacher network, offering guidance beyond mere labels to the student network. This strategy significantly enhances the CSC model{'}s language modeling capabilities, crucial for minimizing over-correction. Importantly, our approach is model-independent and the teacher network does not require task-related pre-training, making it broadly applicable for enhancing various PLM-based CSC models with minimal additional computational resources. Extensive experiments on widely used benchmarks demonstrate that our method achieves new state-of-the-art results. Additionally, we explored the potential of generalizing our method to other non-autoregressive text-generation tasks."
}