@inproceedings{yu-etal-2012-development,
title = "Development of a Web-Scale {C}hinese Word N-gram Corpus with Parts of Speech Information",
author = "Yu, Chi-Hsin and
Tang, Yi-jie and
Chen, Hsin-Hsi",
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/596_Paper.pdf",
pages = "320--324",
abstract = "Web provides a large-scale corpus for researchers to study the language usages in real world. Developing a web-scale corpus needs not only a lot of computation resources, but also great efforts to handle the large variations in the web texts, such as character encoding in processing Chinese web texts. In this paper, we aim to develop a web-scale Chinese word N-gram corpus with parts of speech information called NTU PN-Gram corpus using the ClueWeb09 dataset. We focus on the character encoding and some Chinese-specific issues. The statistics about the dataset is reported. We will make the resulting corpus a public available resource to boost the Chinese language processing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2012-development">
<titleInfo>
<title>Development of a Web-Scale Chinese Word N-gram Corpus with Parts of Speech Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chi-Hsin</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi-jie</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</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>Web provides a large-scale corpus for researchers to study the language usages in real world. Developing a web-scale corpus needs not only a lot of computation resources, but also great efforts to handle the large variations in the web texts, such as character encoding in processing Chinese web texts. In this paper, we aim to develop a web-scale Chinese word N-gram corpus with parts of speech information called NTU PN-Gram corpus using the ClueWeb09 dataset. We focus on the character encoding and some Chinese-specific issues. The statistics about the dataset is reported. We will make the resulting corpus a public available resource to boost the Chinese language processing.</abstract>
<identifier type="citekey">yu-etal-2012-development</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/596_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>320</start>
<end>324</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development of a Web-Scale Chinese Word N-gram Corpus with Parts of Speech Information
%A Yu, Chi-Hsin
%A Tang, Yi-jie
%A Chen, Hsin-Hsi
%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 yu-etal-2012-development
%X Web provides a large-scale corpus for researchers to study the language usages in real world. Developing a web-scale corpus needs not only a lot of computation resources, but also great efforts to handle the large variations in the web texts, such as character encoding in processing Chinese web texts. In this paper, we aim to develop a web-scale Chinese word N-gram corpus with parts of speech information called NTU PN-Gram corpus using the ClueWeb09 dataset. We focus on the character encoding and some Chinese-specific issues. The statistics about the dataset is reported. We will make the resulting corpus a public available resource to boost the Chinese language processing.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/596_Paper.pdf
%P 320-324
Markdown (Informal)
[Development of a Web-Scale Chinese Word N-gram Corpus with Parts of Speech Information](http://www.lrec-conf.org/proceedings/lrec2012/pdf/596_Paper.pdf) (Yu et al., LREC 2012)
ACL