@inproceedings{liu-wang-2016-dictionary,
    title = "How does Dictionary Size Influence Performance of {V}ietnamese Word Segmentation?",
    author = "Liu, Wuying  and
      Wang, Lin",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Grobelnik, Marko  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, Helene  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
    month = may,
    year = "2016",
    address = "Portoro{\v{z}}, Slovenia",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://aclanthology.org/L16-1172/",
    pages = "1079--1083",
    abstract = "Vietnamese word segmentation (VWS) is a challenging basic issue for natural language processing. This paper addresses the problem of how does dictionary size influence VWS performance, proposes two novel measures: square overlap ratio (SOR) and relaxed square overlap ratio (RSOR), and validates their effectiveness. The SOR measure is the product of dictionary overlap ratio and corpus overlap ratio, and the RSOR measure is the relaxed version of SOR measure under an unsupervised condition. The two measures both indicate the suitable degree between segmentation dictionary and object corpus waiting for segmentation. The experimental results show that the more suitable, neither smaller nor larger, dictionary size is better to achieve the state-of-the-art performance for dictionary-based Vietnamese word segmenters."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-wang-2016-dictionary">
    <titleInfo>
        <title>How does Dictionary Size Influence Performance of Vietnamese Word Segmentation?</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Wuying</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lin</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Nicoletta</namePart>
            <namePart type="family">Calzolari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Khalid</namePart>
            <namePart type="family">Choukri</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Thierry</namePart>
            <namePart type="family">Declerck</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sara</namePart>
            <namePart type="family">Goggi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marko</namePart>
            <namePart type="family">Grobelnik</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Bente</namePart>
            <namePart type="family">Maegaard</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joseph</namePart>
            <namePart type="family">Mariani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Helene</namePart>
            <namePart type="family">Mazo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Asuncion</namePart>
            <namePart type="family">Moreno</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jan</namePart>
            <namePart type="family">Odijk</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Stelios</namePart>
            <namePart type="family">Piperidis</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>European Language Resources Association (ELRA)</publisher>
            <place>
                <placeTerm type="text">Portorož, Slovenia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Vietnamese word segmentation (VWS) is a challenging basic issue for natural language processing. This paper addresses the problem of how does dictionary size influence VWS performance, proposes two novel measures: square overlap ratio (SOR) and relaxed square overlap ratio (RSOR), and validates their effectiveness. The SOR measure is the product of dictionary overlap ratio and corpus overlap ratio, and the RSOR measure is the relaxed version of SOR measure under an unsupervised condition. The two measures both indicate the suitable degree between segmentation dictionary and object corpus waiting for segmentation. The experimental results show that the more suitable, neither smaller nor larger, dictionary size is better to achieve the state-of-the-art performance for dictionary-based Vietnamese word segmenters.</abstract>
    <identifier type="citekey">liu-wang-2016-dictionary</identifier>
    <location>
        <url>https://aclanthology.org/L16-1172/</url>
    </location>
    <part>
        <date>2016-05</date>
        <extent unit="page">
            <start>1079</start>
            <end>1083</end>
        </extent>
    </part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How does Dictionary Size Influence Performance of Vietnamese Word Segmentation?
%A Liu, Wuying
%A Wang, Lin
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F liu-wang-2016-dictionary
%X Vietnamese word segmentation (VWS) is a challenging basic issue for natural language processing. This paper addresses the problem of how does dictionary size influence VWS performance, proposes two novel measures: square overlap ratio (SOR) and relaxed square overlap ratio (RSOR), and validates their effectiveness. The SOR measure is the product of dictionary overlap ratio and corpus overlap ratio, and the RSOR measure is the relaxed version of SOR measure under an unsupervised condition. The two measures both indicate the suitable degree between segmentation dictionary and object corpus waiting for segmentation. The experimental results show that the more suitable, neither smaller nor larger, dictionary size is better to achieve the state-of-the-art performance for dictionary-based Vietnamese word segmenters.
%U https://aclanthology.org/L16-1172/
%P 1079-1083
Markdown (Informal)
[How does Dictionary Size Influence Performance of Vietnamese Word Segmentation?](https://aclanthology.org/L16-1172/) (Liu & Wang, LREC 2016)
ACL