EMNLP 2022finding40 citations

Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking

Yinghui Li, Shirong Ma, Qingyu Zhou, Zhongli Li, Li Yangning, Shulin Huang, Ruiyang Liu, Chao Li

Abstract

Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors. Recent researches start from the pretrained knowledge of language models and take multimodal information into CSC models to improve the performance. However, they overlook the rich knowledge in the dictionary, the reference book where one can learn how one character should be pronounced, written, and used. In this paper, we propose the LEAD framework, which renders the CSC model to learn heterogeneous knowledge from the dictionary in terms of phonetics, vision, and meaning. LEAD first constructs positive and negative samples according to the knowledge of character phonetics, glyphs, and definitions in the dictionary. Then a unified contrastive learning-based training scheme is employed to refine the representations of the CSC models. Extensive experiments and detailed analyses on the SIGHAN benchmark datasets demonstrate the effectiveness of our proposed methods.

BibTeX
@inproceedings{li-etal-2022-learning-dictionary,
    title = "Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for {C}hinese Spell Checking",
    author = "Li, Yinghui  and
      Ma, Shirong  and
      Zhou, Qingyu  and
      Li, Zhongli  and
      Yangning, Li  and
      Huang, Shulin  and
      Liu, Ruiyang  and
      Li, Chao  and
      Cao, Yunbo  and
      Zheng, Haitao",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-emnlp.18/",
    doi = "10.18653/v1/2022.findings-emnlp.18",
    pages = "238--249"
}
Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking · EMNLP 2022