@inproceedings{higashiyama-etal-2021-text,
    title = "A Text Editing Approach to Joint {J}apanese Word Segmentation, {POS} Tagging, and Lexical Normalization",
    author = "Higashiyama, Shohei  and
      Utiyama, Masao  and
      Watanabe, Taro  and
      Sumita, Eiichiro",
    booktitle = "Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021)",
    month = nov,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.wnut-1.9",
    doi = "10.18653/v1/2021.wnut-1.9",
    pages = "67--80",
    abstract = "Lexical normalization, in addition to word segmentation and part-of-speech tagging, is a fundamental task for Japanese user-generated text processing. In this paper, we propose a text editing model to solve the three task jointly and methods of pseudo-labeled data generation to overcome the problem of data deficiency. Our experiments showed that the proposed model achieved better normalization performance when trained on more diverse pseudo-labeled data.",
}