@inproceedings{tolmachev-etal-2018-juman,
title = "{J}uman++: A Morphological Analysis Toolkit for Scriptio Continua",
author = "Tolmachev, Arseny and
Kawahara, Daisuke and
Kurohashi, Sadao",
editor = "Blanco, Eduardo and
Lu, Wei",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D18-2010/",
doi = "10.18653/v1/D18-2010",
pages = "54--59",
abstract = "We present a three-part toolkit for developing morphological analyzers for languages without natural word boundaries. The first part is a C++11/14 lattice-based morphological analysis library that uses a combination of linear and recurrent neural net language models for analysis. The other parts are a tool for exposing problems in the trained model and a partial annotation tool. Our morphological analyzer of Japanese achieves new SOTA on Jumandic-based corpora while being 250 times faster than the previous one. We also perform a small experiment and quantitive analysis and experience of using development tools. All components of the toolkit is open source and available under a permissive Apache 2 License."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tolmachev-etal-2018-juman">
<titleInfo>
<title>Juman++: A Morphological Analysis Toolkit for Scriptio Continua</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arseny</namePart>
<namePart type="family">Tolmachev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eduardo</namePart>
<namePart type="family">Blanco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present a three-part toolkit for developing morphological analyzers for languages without natural word boundaries. The first part is a C++11/14 lattice-based morphological analysis library that uses a combination of linear and recurrent neural net language models for analysis. The other parts are a tool for exposing problems in the trained model and a partial annotation tool. Our morphological analyzer of Japanese achieves new SOTA on Jumandic-based corpora while being 250 times faster than the previous one. We also perform a small experiment and quantitive analysis and experience of using development tools. All components of the toolkit is open source and available under a permissive Apache 2 License.</abstract>
<identifier type="citekey">tolmachev-etal-2018-juman</identifier>
<identifier type="doi">10.18653/v1/D18-2010</identifier>
<location>
<url>https://aclanthology.org/D18-2010/</url>
</location>
<part>
<date>2018-11</date>
<extent unit="page">
<start>54</start>
<end>59</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Juman++: A Morphological Analysis Toolkit for Scriptio Continua
%A Tolmachev, Arseny
%A Kawahara, Daisuke
%A Kurohashi, Sadao
%Y Blanco, Eduardo
%Y Lu, Wei
%S Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2018
%8 November
%I Association for Computational Linguistics
%C Brussels, Belgium
%F tolmachev-etal-2018-juman
%X We present a three-part toolkit for developing morphological analyzers for languages without natural word boundaries. The first part is a C++11/14 lattice-based morphological analysis library that uses a combination of linear and recurrent neural net language models for analysis. The other parts are a tool for exposing problems in the trained model and a partial annotation tool. Our morphological analyzer of Japanese achieves new SOTA on Jumandic-based corpora while being 250 times faster than the previous one. We also perform a small experiment and quantitive analysis and experience of using development tools. All components of the toolkit is open source and available under a permissive Apache 2 License.
%R 10.18653/v1/D18-2010
%U https://aclanthology.org/D18-2010/
%U https://doi.org/10.18653/v1/D18-2010
%P 54-59
Markdown (Informal)
[Juman++: A Morphological Analysis Toolkit for Scriptio Continua](https://aclanthology.org/D18-2010/) (Tolmachev et al., EMNLP 2018)
ACL
- Arseny Tolmachev, Daisuke Kawahara, and Sadao Kurohashi. 2018. Juman++: A Morphological Analysis Toolkit for Scriptio Continua. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 54–59, Brussels, Belgium. Association for Computational Linguistics.