@inproceedings{dinh-etal-2008-word,
title = "Word Segmentation of {V}ietnamese Texts: a Comparison of Approaches",
author = "{\DJ}inh, Quang Thắng and
L{\^e}, Hồng Phương and
Nguyễn, Thị Minh Huyền and
Nguyễn, Cẩm T{\'u} and
Rossignol, Mathias and
V{\~u}, Xu{\^a}n Lương",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/493_paper.pdf",
abstract = "We present in this paper a comparison between three segmentation systems for the Vietnamese language. Indeed, the majority of Vietnamese words is built by semantic composition from about 7,000 syllables, which also have a meaning as isolated words. So the identification of word boundaries in a text is not a simple task, and ambiguities often appear. Beyond the presentation of the tested systems, we also propose a standard definition for word segmentation in Vietnamese, and introduce a reference corpus developed for the purpose of evaluating such a task. The results observed confirm that it can be relatively well treated by automatic means, although a solution needs to be found to take into account out-of-vocabulary words.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dinh-etal-2008-word">
<titleInfo>
<title>Word Segmentation of Vietnamese Texts: a Comparison of Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Quang</namePart>
<namePart type="given">Thắng</namePart>
<namePart type="family">Đinh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hồng</namePart>
<namePart type="given">Phương</namePart>
<namePart type="family">Lê</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thị</namePart>
<namePart type="given">Minh</namePart>
<namePart type="given">Huyền</namePart>
<namePart type="family">Nguyễn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cẩm</namePart>
<namePart type="given">Tú</namePart>
<namePart type="family">Nguyễn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathias</namePart>
<namePart type="family">Rossignol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuân</namePart>
<namePart type="given">Lương</namePart>
<namePart type="family">Vũ</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present in this paper a comparison between three segmentation systems for the Vietnamese language. Indeed, the majority of Vietnamese words is built by semantic composition from about 7,000 syllables, which also have a meaning as isolated words. So the identification of word boundaries in a text is not a simple task, and ambiguities often appear. Beyond the presentation of the tested systems, we also propose a standard definition for word segmentation in Vietnamese, and introduce a reference corpus developed for the purpose of evaluating such a task. The results observed confirm that it can be relatively well treated by automatic means, although a solution needs to be found to take into account out-of-vocabulary words.</abstract>
<identifier type="citekey">dinh-etal-2008-word</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/493_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Segmentation of Vietnamese Texts: a Comparison of Approaches
%A Đinh, Quang Thắng
%A Lê, Hồng Phương
%A Nguyễn, Thị Minh Huyền
%A Nguyễn, Cẩm Tú
%A Rossignol, Mathias
%A Vũ, Xuân Lương
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F dinh-etal-2008-word
%X We present in this paper a comparison between three segmentation systems for the Vietnamese language. Indeed, the majority of Vietnamese words is built by semantic composition from about 7,000 syllables, which also have a meaning as isolated words. So the identification of word boundaries in a text is not a simple task, and ambiguities often appear. Beyond the presentation of the tested systems, we also propose a standard definition for word segmentation in Vietnamese, and introduce a reference corpus developed for the purpose of evaluating such a task. The results observed confirm that it can be relatively well treated by automatic means, although a solution needs to be found to take into account out-of-vocabulary words.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/493_paper.pdf
Markdown (Informal)
[Word Segmentation of Vietnamese Texts: a Comparison of Approaches](http://www.lrec-conf.org/proceedings/lrec2008/pdf/493_paper.pdf) (Đinh et al., LREC 2008)
ACL
- Quang Thắng Đinh, Hồng Phương Lê, Thị Minh Huyền Nguyễn, Cẩm Tú Nguyễn, Mathias Rossignol, and Xuân Lương Vũ. 2008. Word Segmentation of Vietnamese Texts: a Comparison of Approaches. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).