@inproceedings{xia-etal-2012-cltc,
title = "{CLTC}: A {C}hinese-{E}nglish Cross-lingual Topic Corpus",
author = "Xia, Yunqing and
Tang, Guoyu and
Jin, Peng and
Yang, Xia",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/389_Paper.pdf",
pages = "532--537",
abstract = "Cross-lingual topic detection within text is a feasible solution to resolving the language barrier in accessing the information. This paper presents a Chinese-English cross-lingual topic corpus (CLTC), in which 90,000 Chinese articles and 90,000 English articles are organized within 150 topics. Compared with TDT corpora, CLTC has three advantages. First, CLTC is bigger in size. This makes it possible to evaluate the large-scale cross-lingual text clustering methods. Second, articles are evenly distributed within the topics. Thus it can be used to produce test datasets for different purposes. Third, CLTC can be used as a cross-lingual comparable corpus to develop methods for cross-lingual information access. A preliminary evaluation with CLTC corpus indicates that the corpus is effective in evaluating cross-lingual topic detection methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xia-etal-2012-cltc">
<titleInfo>
<title>CLTC: A Chinese-English Cross-lingual Topic Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunqing</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoyu</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xia</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-lingual topic detection within text is a feasible solution to resolving the language barrier in accessing the information. This paper presents a Chinese-English cross-lingual topic corpus (CLTC), in which 90,000 Chinese articles and 90,000 English articles are organized within 150 topics. Compared with TDT corpora, CLTC has three advantages. First, CLTC is bigger in size. This makes it possible to evaluate the large-scale cross-lingual text clustering methods. Second, articles are evenly distributed within the topics. Thus it can be used to produce test datasets for different purposes. Third, CLTC can be used as a cross-lingual comparable corpus to develop methods for cross-lingual information access. A preliminary evaluation with CLTC corpus indicates that the corpus is effective in evaluating cross-lingual topic detection methods.</abstract>
<identifier type="citekey">xia-etal-2012-cltc</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/389_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>532</start>
<end>537</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLTC: A Chinese-English Cross-lingual Topic Corpus
%A Xia, Yunqing
%A Tang, Guoyu
%A Jin, Peng
%A Yang, Xia
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F xia-etal-2012-cltc
%X Cross-lingual topic detection within text is a feasible solution to resolving the language barrier in accessing the information. This paper presents a Chinese-English cross-lingual topic corpus (CLTC), in which 90,000 Chinese articles and 90,000 English articles are organized within 150 topics. Compared with TDT corpora, CLTC has three advantages. First, CLTC is bigger in size. This makes it possible to evaluate the large-scale cross-lingual text clustering methods. Second, articles are evenly distributed within the topics. Thus it can be used to produce test datasets for different purposes. Third, CLTC can be used as a cross-lingual comparable corpus to develop methods for cross-lingual information access. A preliminary evaluation with CLTC corpus indicates that the corpus is effective in evaluating cross-lingual topic detection methods.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/389_Paper.pdf
%P 532-537
Markdown (Informal)
[CLTC: A Chinese-English Cross-lingual Topic Corpus](http://www.lrec-conf.org/proceedings/lrec2012/pdf/389_Paper.pdf) (Xia et al., LREC 2012)
ACL
- Yunqing Xia, Guoyu Tang, Peng Jin, and Xia Yang. 2012. CLTC: A Chinese-English Cross-lingual Topic Corpus. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 532–537, Istanbul, Turkey. European Language Resources Association (ELRA).