@inproceedings{tong-etal-2022-word,
title = "Word Segmentation by Separation Inference for {E}ast {A}sian Languages",
author = "Tong, Yu and
Guo, Jingzhi and
Zhou, Jizhe and
Chen, Ge and
Zheng, Guokai",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.309",
doi = "10.18653/v1/2022.findings-acl.309",
pages = "3924--3934",
abstract = "Chinese Word Segmentation (CWS) intends to divide a raw sentence into words through sequence labeling. Thinking in reverse, CWS can also be viewed as a process of grouping a sequence of characters into a sequence of words. In such a way, CWS is reformed as a separation inference task in every adjacent character pair. Since every character is either connected or not connected to the others, the tagging schema is simplified as two tags {``}Connection{''} (C) or {``}NoConnection{''} (NC). Therefore, bigram is specially tailored for {``}C-NC{''} to model the separation state of every two consecutive characters. Our Separation Inference (SpIn) framework is evaluated on five public datasets, is demonstrated to work for machine learning and deep learning models, and outperforms state-of-the-art performance for CWS in all experiments. Performance boosts on Japanese Word Segmentation (JWS) and Korean Word Segmentation (KWS) further prove the framework is universal and effective for East Asian Languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tong-etal-2022-word">
<titleInfo>
<title>Word Segmentation by Separation Inference for East Asian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingzhi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jizhe</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ge</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guokai</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Chinese Word Segmentation (CWS) intends to divide a raw sentence into words through sequence labeling. Thinking in reverse, CWS can also be viewed as a process of grouping a sequence of characters into a sequence of words. In such a way, CWS is reformed as a separation inference task in every adjacent character pair. Since every character is either connected or not connected to the others, the tagging schema is simplified as two tags “Connection” (C) or “NoConnection” (NC). Therefore, bigram is specially tailored for “C-NC” to model the separation state of every two consecutive characters. Our Separation Inference (SpIn) framework is evaluated on five public datasets, is demonstrated to work for machine learning and deep learning models, and outperforms state-of-the-art performance for CWS in all experiments. Performance boosts on Japanese Word Segmentation (JWS) and Korean Word Segmentation (KWS) further prove the framework is universal and effective for East Asian Languages.</abstract>
<identifier type="citekey">tong-etal-2022-word</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.309</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.309</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>3924</start>
<end>3934</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Segmentation by Separation Inference for East Asian Languages
%A Tong, Yu
%A Guo, Jingzhi
%A Zhou, Jizhe
%A Chen, Ge
%A Zheng, Guokai
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F tong-etal-2022-word
%X Chinese Word Segmentation (CWS) intends to divide a raw sentence into words through sequence labeling. Thinking in reverse, CWS can also be viewed as a process of grouping a sequence of characters into a sequence of words. In such a way, CWS is reformed as a separation inference task in every adjacent character pair. Since every character is either connected or not connected to the others, the tagging schema is simplified as two tags “Connection” (C) or “NoConnection” (NC). Therefore, bigram is specially tailored for “C-NC” to model the separation state of every two consecutive characters. Our Separation Inference (SpIn) framework is evaluated on five public datasets, is demonstrated to work for machine learning and deep learning models, and outperforms state-of-the-art performance for CWS in all experiments. Performance boosts on Japanese Word Segmentation (JWS) and Korean Word Segmentation (KWS) further prove the framework is universal and effective for East Asian Languages.
%R 10.18653/v1/2022.findings-acl.309
%U https://aclanthology.org/2022.findings-acl.309
%U https://doi.org/10.18653/v1/2022.findings-acl.309
%P 3924-3934
Markdown (Informal)
[Word Segmentation by Separation Inference for East Asian Languages](https://aclanthology.org/2022.findings-acl.309) (Tong et al., Findings 2022)
ACL