@inproceedings{mccann-2020-fugashi,
title = "fugashi, a Tool for Tokenizing {J}apanese in Python",
author = "McCann, Paul",
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://aclanthology.org/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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mccann-2020-fugashi">
<titleInfo>
<title>fugashi, a Tool for Tokenizing Japanese in Python</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">McCann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">mccann-2020-fugashi</identifier>
<identifier type="doi">10.18653/v1/2020.nlposs-1.7</identifier>
<location>
<url>https://aclanthology.org/2020.nlposs-1.7</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>44</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T fugashi, a Tool for Tokenizing Japanese in Python
%A McCann, Paul
%S Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F mccann-2020-fugashi
%X 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.
%R 10.18653/v1/2020.nlposs-1.7
%U https://aclanthology.org/2020.nlposs-1.7
%U https://doi.org/10.18653/v1/2020.nlposs-1.7
%P 44-51
Markdown (Informal)
[fugashi, a Tool for Tokenizing Japanese in Python](https://aclanthology.org/2020.nlposs-1.7) (McCann, NLPOSS 2020)
ACL