@inproceedings{mccann-2020-fugashi,
    title = "fugashi, a Tool for Tokenizing {J}apanese in Python",
    author = "McCann, Paul",
    editor = "Park, Eunjeong L.  and
      Hagiwara, Masato  and
      Milajevs, Dmitrijs  and
      Liu, Nelson F.  and
      Chauhan, Geeticka  and
      Tan, Liling",
    booktitle = "Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.nlposs-1.7/",
    doi = "10.18653/v1/2020.nlposs-1.7",
    pages = "44--51",
    abstract = "Recent years have seen an increase in the number of large-scale multilingual NLP projects. However, even in such projects, languages with special processing requirements are often excluded. One such language is Japanese. Japanese is written without spaces, tokenization is non-trivial, and while high quality open source tokenizers exist they can be hard to use and lack English documentation. This paper introduces fugashi, a MeCab wrapper for Python, and gives an introduction to tokenizing Japanese."
}