<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fujii-etal-2017-nonparametric">
    <titleInfo>
        <title>Nonparametric Bayesian Semi-supervised Word Segmentation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ryo</namePart>
        <namePart type="family">Fujii</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryo</namePart>
        <namePart type="family">Domoto</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Daichi</namePart>
        <namePart type="family">Mochihashi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>This paper presents a novel hybrid generative/discriminative model of word segmentation based on nonparametric Bayesian methods. Unlike ordinary discriminative word segmentation which relies only on labeled data, our semi-supervised model also leverages a huge amounts of unlabeled text to automatically learn new “words”, and further constrains them by using a labeled data to segment non-standard texts such as those found in social networking services. Specifically, our hybrid model combines a discriminative classifier (CRF; Lafferty et al. (2001) and unsupervised word segmentation (NPYLM; Mochihashi et al. (2009)), with a transparent exchange of information between these two model structures within the semi-supervised framework (JESS-CM; Suzuki and Isozaki (2008)). We confirmed that it can appropriately segment non-standard texts like those in Twitter and Weibo and has nearly state-of-the-art accuracy on standard datasets in Japanese, Chinese, and Thai.</abstract>
    <identifier type="citekey">fujii-etal-2017-nonparametric</identifier>
    <identifier type="doi">10.1162/tacl_a_00054</identifier>
    <location>
        <url>https://aclanthology.org/Q17-1013</url>
    </location>
    <part>
        <date>2017</date>
        <detail type="volume"><number>5</number></detail>
        <extent unit="page">
            <start>179</start>
            <end>189</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Nonparametric Bayesian Semi-supervised Word Segmentation
%A Fujii, Ryo
%A Domoto, Ryo
%A Mochihashi, Daichi
%J Transactions of the Association for Computational Linguistics
%D 2017
%V 5
%I MIT Press
%C Cambridge, MA
%F fujii-etal-2017-nonparametric
%X This paper presents a novel hybrid generative/discriminative model of word segmentation based on nonparametric Bayesian methods. Unlike ordinary discriminative word segmentation which relies only on labeled data, our semi-supervised model also leverages a huge amounts of unlabeled text to automatically learn new “words”, and further constrains them by using a labeled data to segment non-standard texts such as those found in social networking services. Specifically, our hybrid model combines a discriminative classifier (CRF; Lafferty et al. (2001) and unsupervised word segmentation (NPYLM; Mochihashi et al. (2009)), with a transparent exchange of information between these two model structures within the semi-supervised framework (JESS-CM; Suzuki and Isozaki (2008)). We confirmed that it can appropriately segment non-standard texts like those in Twitter and Weibo and has nearly state-of-the-art accuracy on standard datasets in Japanese, Chinese, and Thai.
%R 10.1162/tacl_a_00054
%U https://aclanthology.org/Q17-1013
%U https://doi.org/10.1162/tacl_a_00054
%P 179-189

Markdown (Informal)

[Nonparametric Bayesian Semi-supervised Word Segmentation](https://aclanthology.org/Q17-1013) (Fujii et al., TACL 2017)

• Nonparametric Bayesian Semi-supervised Word Segmentation (Fujii et al., TACL 2017)

ACL

• Ryo Fujii, Ryo Domoto, and Daichi Mochihashi. 2017. Nonparametric Bayesian Semi-supervised Word Segmentation. Transactions of the Association for Computational Linguistics, 5:179–189.