@inproceedings{higashiyama-etal-2019-incorporating,
title = "Incorporating Word Attention into Character-Based Word Segmentation",
author = "Higashiyama, Shohei and
Utiyama, Masao and
Sumita, Eiichiro and
Ideuchi, Masao and
Oida, Yoshiaki and
Sakamoto, Yohei and
Okada, Isaac",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1276",
doi = "10.18653/v1/N19-1276",
pages = "2699--2709",
abstract = "Neural network models have been actively applied to word segmentation, especially Chinese, because of the ability to minimize the effort in feature engineering. Typical segmentation models are categorized as character-based, for conducting exact inference, or word-based, for utilizing word-level information. We propose a character-based model utilizing word information to leverage the advantages of both types of models. Our model learns the importance of multiple candidate words for a character on the basis of an attention mechanism, and makes use of it for segmentation decisions. The experimental results show that our model achieves better performance than the state-of-the-art models on both Japanese and Chinese benchmark datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="higashiyama-etal-2019-incorporating">
<titleInfo>
<title>Incorporating Word Attention into Character-Based Word Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shohei</namePart>
<namePart type="family">Higashiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Ideuchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshiaki</namePart>
<namePart type="family">Oida</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yohei</namePart>
<namePart type="family">Sakamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaac</namePart>
<namePart type="family">Okada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Neural network models have been actively applied to word segmentation, especially Chinese, because of the ability to minimize the effort in feature engineering. Typical segmentation models are categorized as character-based, for conducting exact inference, or word-based, for utilizing word-level information. We propose a character-based model utilizing word information to leverage the advantages of both types of models. Our model learns the importance of multiple candidate words for a character on the basis of an attention mechanism, and makes use of it for segmentation decisions. The experimental results show that our model achieves better performance than the state-of-the-art models on both Japanese and Chinese benchmark datasets.</abstract>
<identifier type="citekey">higashiyama-etal-2019-incorporating</identifier>
<identifier type="doi">10.18653/v1/N19-1276</identifier>
<location>
<url>https://aclanthology.org/N19-1276</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2699</start>
<end>2709</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Word Attention into Character-Based Word Segmentation
%A Higashiyama, Shohei
%A Utiyama, Masao
%A Sumita, Eiichiro
%A Ideuchi, Masao
%A Oida, Yoshiaki
%A Sakamoto, Yohei
%A Okada, Isaac
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F higashiyama-etal-2019-incorporating
%X Neural network models have been actively applied to word segmentation, especially Chinese, because of the ability to minimize the effort in feature engineering. Typical segmentation models are categorized as character-based, for conducting exact inference, or word-based, for utilizing word-level information. We propose a character-based model utilizing word information to leverage the advantages of both types of models. Our model learns the importance of multiple candidate words for a character on the basis of an attention mechanism, and makes use of it for segmentation decisions. The experimental results show that our model achieves better performance than the state-of-the-art models on both Japanese and Chinese benchmark datasets.
%R 10.18653/v1/N19-1276
%U https://aclanthology.org/N19-1276
%U https://doi.org/10.18653/v1/N19-1276
%P 2699-2709
Markdown (Informal)
[Incorporating Word Attention into Character-Based Word Segmentation](https://aclanthology.org/N19-1276) (Higashiyama et al., NAACL 2019)
ACL
- Shohei Higashiyama, Masao Utiyama, Eiichiro Sumita, Masao Ideuchi, Yoshiaki Oida, Yohei Sakamoto, and Isaac Okada. 2019. Incorporating Word Attention into Character-Based Word Segmentation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 2699–2709, Minneapolis, Minnesota. Association for Computational Linguistics.