@inproceedings{yang-etal-2019-subword,
title = "Subword Encoding in Lattice {LSTM} for {C}hinese Word Segmentation",
author = "Yang, Jie and
Zhang, Yue and
Liang, Shuailong",
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/N19-1278",
doi = "10.18653/v1/N19-1278",
pages = "2720--2725",
abstract = "We investigate subword information for Chinese word segmentation, by integrating sub word embeddings trained using byte-pair encoding into a Lattice LSTM (LaLSTM) network over a character sequence. Experiments on standard benchmark show that subword information brings significant gains over strong character-based segmentation models. To our knowledge, this is the first research on the effectiveness of subwords on neural word segmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2019-subword">
<titleInfo>
<title>Subword Encoding in Lattice LSTM for Chinese Word Segmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuailong</namePart>
<namePart type="family">Liang</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>We investigate subword information for Chinese word segmentation, by integrating sub word embeddings trained using byte-pair encoding into a Lattice LSTM (LaLSTM) network over a character sequence. Experiments on standard benchmark show that subword information brings significant gains over strong character-based segmentation models. To our knowledge, this is the first research on the effectiveness of subwords on neural word segmentation.</abstract>
<identifier type="citekey">yang-etal-2019-subword</identifier>
<identifier type="doi">10.18653/v1/N19-1278</identifier>
<location>
<url>https://aclanthology.org/N19-1278</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2720</start>
<end>2725</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Subword Encoding in Lattice LSTM for Chinese Word Segmentation
%A Yang, Jie
%A Zhang, Yue
%A Liang, Shuailong
%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 yang-etal-2019-subword
%X We investigate subword information for Chinese word segmentation, by integrating sub word embeddings trained using byte-pair encoding into a Lattice LSTM (LaLSTM) network over a character sequence. Experiments on standard benchmark show that subword information brings significant gains over strong character-based segmentation models. To our knowledge, this is the first research on the effectiveness of subwords on neural word segmentation.
%R 10.18653/v1/N19-1278
%U https://aclanthology.org/N19-1278
%U https://doi.org/10.18653/v1/N19-1278
%P 2720-2725
Markdown (Informal)
[Subword Encoding in Lattice LSTM for Chinese Word Segmentation](https://aclanthology.org/N19-1278) (Yang et al., NAACL 2019)
ACL
- Jie Yang, Yue Zhang, and Shuailong Liang. 2019. Subword Encoding in Lattice LSTM for Chinese 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 2720–2725, Minneapolis, Minnesota. Association for Computational Linguistics.