@inproceedings{tian-etal-2014-um,
title = "{UM}-Corpus: A Large {E}nglish-{C}hinese Parallel Corpus for Statistical Machine Translation",
author = "Tian, Liang and
Wong, Derek F. and
Chao, Lidia S. and
Quaresma, Paulo and
Oliveira, Francisco and
Lu, Yi and
Li, Shuo and
Wang, Yiming and
Wang, Longyue",
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/774_Paper.pdf",
pages = "1837--1842",
abstract = "Parallel corpus is a valuable resource for cross-language information retrieval and data-driven natural language processing systems, especially for Statistical Machine Translation (SMT). However, most existing parallel corpora to Chinese are subject to in-house use, while others are domain specific and limited in size. To a certain degree, this limits the SMT research. This paper describes the acquisition of a large scale and high quality parallel corpora for English and Chinese. The corpora constructed in this paper contain about 15 million English-Chinese (E-C) parallel sentences, and more than 2 million training data and 5,000 testing sentences are made publicly available. Different from previous work, the corpus is designed to embrace eight different domains. Some of them are further categorized into different topics. The corpus will be released to the research community, which is available at the NLP2CT website.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tian-etal-2014-um">
<titleInfo>
<title>UM-Corpus: A Large English-Chinese Parallel Corpus for Statistical Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Derek</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidia</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Chao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paulo</namePart>
<namePart type="family">Quaresma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francisco</namePart>
<namePart type="family">Oliveira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiming</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Longyue</namePart>
<namePart type="family">Wang</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 corpus is a valuable resource for cross-language information retrieval and data-driven natural language processing systems, especially for Statistical Machine Translation (SMT). However, most existing parallel corpora to Chinese are subject to in-house use, while others are domain specific and limited in size. To a certain degree, this limits the SMT research. This paper describes the acquisition of a large scale and high quality parallel corpora for English and Chinese. The corpora constructed in this paper contain about 15 million English-Chinese (E-C) parallel sentences, and more than 2 million training data and 5,000 testing sentences are made publicly available. Different from previous work, the corpus is designed to embrace eight different domains. Some of them are further categorized into different topics. The corpus will be released to the research community, which is available at the NLP2CT website.</abstract>
<identifier type="citekey">tian-etal-2014-um</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/774_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1837</start>
<end>1842</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UM-Corpus: A Large English-Chinese Parallel Corpus for Statistical Machine Translation
%A Tian, Liang
%A Wong, Derek F.
%A Chao, Lidia S.
%A Quaresma, Paulo
%A Oliveira, Francisco
%A Lu, Yi
%A Li, Shuo
%A Wang, Yiming
%A Wang, Longyue
%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 tian-etal-2014-um
%X Parallel corpus is a valuable resource for cross-language information retrieval and data-driven natural language processing systems, especially for Statistical Machine Translation (SMT). However, most existing parallel corpora to Chinese are subject to in-house use, while others are domain specific and limited in size. To a certain degree, this limits the SMT research. This paper describes the acquisition of a large scale and high quality parallel corpora for English and Chinese. The corpora constructed in this paper contain about 15 million English-Chinese (E-C) parallel sentences, and more than 2 million training data and 5,000 testing sentences are made publicly available. Different from previous work, the corpus is designed to embrace eight different domains. Some of them are further categorized into different topics. The corpus will be released to the research community, which is available at the NLP2CT website.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/774_Paper.pdf
%P 1837-1842
Markdown (Informal)
[UM-Corpus: A Large English-Chinese Parallel Corpus for Statistical Machine Translation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/774_Paper.pdf) (Tian et al., LREC 2014)
ACL
- Liang Tian, Derek F. Wong, Lidia S. Chao, Paulo Quaresma, Francisco Oliveira, Yi Lu, Shuo Li, Yiming Wang, and Longyue Wang. 2014. UM-Corpus: A Large English-Chinese Parallel Corpus for Statistical Machine Translation. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1837–1842, Reykjavik, Iceland. European Language Resources Association (ELRA).