@inproceedings{dalianis-etal-2010-creating,
title = "Creating a Reusable {E}nglish-{C}hinese Parallel Corpus for Bilingual Dictionary Construction",
author = "Dalianis, Hercules and
Xing, Hao-chun and
Zhang, Xin",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/13_Paper.pdf",
abstract = "This paper first describes an experiment to construct an English-Chinese parallel corpus, then applying the Uplug word alignment tool on the corpus and finally produce and evaluate an English-Chinese word list. The Stockholm English-Chinese Parallel Corpus (SEC) was created by downloading English-Chinese parallel corpora from a Chinese web site containing law texts that have been manually translated from Chinese to English. The parallel corpus contains 104 563 Chinese characters equivalent to 59 918 Chinese words, and the corresponding English corpus contains 75 766 English words. However Chinese writing does not utilize any delimiters to mark word boundaries so we had to carry out word segmentation as a preprocessing step on the Chinese corpus. Moreover since the parallel corpus is downloaded from Internet the corpus is noisy regarding to alignment between corresponding translated sentences. Therefore we used 60 hours of manually work to align the sentences in the English and Chinese parallel corpus before performing automatic word alignment using Uplug. The word alignment with Uplug was carried out from English to Chinese. Nine respondents evaluated the resulting English-Chinese word list with frequency equal to or above three and we obtained an accuracy of 73.1 percent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dalianis-etal-2010-creating">
<titleInfo>
<title>Creating a Reusable English-Chinese Parallel Corpus for Bilingual Dictionary Construction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hercules</namePart>
<namePart type="family">Dalianis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao-chun</namePart>
<namePart type="family">Xing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper first describes an experiment to construct an English-Chinese parallel corpus, then applying the Uplug word alignment tool on the corpus and finally produce and evaluate an English-Chinese word list. The Stockholm English-Chinese Parallel Corpus (SEC) was created by downloading English-Chinese parallel corpora from a Chinese web site containing law texts that have been manually translated from Chinese to English. The parallel corpus contains 104 563 Chinese characters equivalent to 59 918 Chinese words, and the corresponding English corpus contains 75 766 English words. However Chinese writing does not utilize any delimiters to mark word boundaries so we had to carry out word segmentation as a preprocessing step on the Chinese corpus. Moreover since the parallel corpus is downloaded from Internet the corpus is noisy regarding to alignment between corresponding translated sentences. Therefore we used 60 hours of manually work to align the sentences in the English and Chinese parallel corpus before performing automatic word alignment using Uplug. The word alignment with Uplug was carried out from English to Chinese. Nine respondents evaluated the resulting English-Chinese word list with frequency equal to or above three and we obtained an accuracy of 73.1 percent.</abstract>
<identifier type="citekey">dalianis-etal-2010-creating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/13_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating a Reusable English-Chinese Parallel Corpus for Bilingual Dictionary Construction
%A Dalianis, Hercules
%A Xing, Hao-chun
%A Zhang, Xin
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F dalianis-etal-2010-creating
%X This paper first describes an experiment to construct an English-Chinese parallel corpus, then applying the Uplug word alignment tool on the corpus and finally produce and evaluate an English-Chinese word list. The Stockholm English-Chinese Parallel Corpus (SEC) was created by downloading English-Chinese parallel corpora from a Chinese web site containing law texts that have been manually translated from Chinese to English. The parallel corpus contains 104 563 Chinese characters equivalent to 59 918 Chinese words, and the corresponding English corpus contains 75 766 English words. However Chinese writing does not utilize any delimiters to mark word boundaries so we had to carry out word segmentation as a preprocessing step on the Chinese corpus. Moreover since the parallel corpus is downloaded from Internet the corpus is noisy regarding to alignment between corresponding translated sentences. Therefore we used 60 hours of manually work to align the sentences in the English and Chinese parallel corpus before performing automatic word alignment using Uplug. The word alignment with Uplug was carried out from English to Chinese. Nine respondents evaluated the resulting English-Chinese word list with frequency equal to or above three and we obtained an accuracy of 73.1 percent.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/13_Paper.pdf
Markdown (Informal)
[Creating a Reusable English-Chinese Parallel Corpus for Bilingual Dictionary Construction](http://www.lrec-conf.org/proceedings/lrec2010/pdf/13_Paper.pdf) (Dalianis et al., LREC 2010)
ACL