@inproceedings{chu-etal-2014-constructing,
title = "Constructing a {C}hinese{---}{J}apanese Parallel Corpus from {W}ikipedia",
author = "Chu, Chenhui and
Nakazawa, Toshiaki and
Kurohashi, Sadao",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/21_Paper.pdf",
pages = "642--647",
abstract = "Parallel corpora are crucial for statistical machine translation (SMT). However, they are quite scarce for most language pairs, such as Chinese―Japanese. As comparable corpora are far more available, many studies have been conducted to automatically construct parallel corpora from comparable corpora. This paper presents a robust parallel sentence extraction system for constructing a Chinese―Japanese parallel corpus from Wikipedia. The system is inspired by previous studies that mainly consist of a parallel sentence candidate filter and a binary classifier for parallel sentence identification. We improve the system by using the common Chinese characters for filtering and two novel feature sets for classification. Experiments show that our system performs significantly better than the previous studies for both accuracy in parallel sentence extraction and SMT performance. Using the system, we construct a Chinese―Japanese parallel corpus with more than 126k highly accurate parallel sentences from Wikipedia. The constructed parallel corpus is freely available at \url{http://orchid.kuee.kyoto-u.ac.jp/chu/resource/wiki_zh_ja.tgz}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2014-constructing">
<titleInfo>
<title>Constructing a Chinese—Japanese Parallel Corpus from Wikipedia</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Chu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel corpora are crucial for statistical machine translation (SMT). However, they are quite scarce for most language pairs, such as Chinese―Japanese. As comparable corpora are far more available, many studies have been conducted to automatically construct parallel corpora from comparable corpora. This paper presents a robust parallel sentence extraction system for constructing a Chinese―Japanese parallel corpus from Wikipedia. The system is inspired by previous studies that mainly consist of a parallel sentence candidate filter and a binary classifier for parallel sentence identification. We improve the system by using the common Chinese characters for filtering and two novel feature sets for classification. Experiments show that our system performs significantly better than the previous studies for both accuracy in parallel sentence extraction and SMT performance. Using the system, we construct a Chinese―Japanese parallel corpus with more than 126k highly accurate parallel sentences from Wikipedia. The constructed parallel corpus is freely available at http://orchid.kuee.kyoto-u.ac.jp/chu/resource/wiki_zh_ja.tgz.</abstract>
<identifier type="citekey">chu-etal-2014-constructing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/21_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>642</start>
<end>647</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing a Chinese—Japanese Parallel Corpus from Wikipedia
%A Chu, Chenhui
%A Nakazawa, Toshiaki
%A Kurohashi, Sadao
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F chu-etal-2014-constructing
%X Parallel corpora are crucial for statistical machine translation (SMT). However, they are quite scarce for most language pairs, such as Chinese―Japanese. As comparable corpora are far more available, many studies have been conducted to automatically construct parallel corpora from comparable corpora. This paper presents a robust parallel sentence extraction system for constructing a Chinese―Japanese parallel corpus from Wikipedia. The system is inspired by previous studies that mainly consist of a parallel sentence candidate filter and a binary classifier for parallel sentence identification. We improve the system by using the common Chinese characters for filtering and two novel feature sets for classification. Experiments show that our system performs significantly better than the previous studies for both accuracy in parallel sentence extraction and SMT performance. Using the system, we construct a Chinese―Japanese parallel corpus with more than 126k highly accurate parallel sentences from Wikipedia. The constructed parallel corpus is freely available at http://orchid.kuee.kyoto-u.ac.jp/chu/resource/wiki_zh_ja.tgz.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/21_Paper.pdf
%P 642-647
Markdown (Informal)
[Constructing a Chinese—Japanese Parallel Corpus from Wikipedia](http://www.lrec-conf.org/proceedings/lrec2014/pdf/21_Paper.pdf) (Chu et al., LREC 2014)
ACL