@inproceedings{tsvetkov-wintner-2010-automatic,
title = "Automatic Acquisition of Parallel Corpora from Websites with Dynamic Content",
author = "Tsvetkov, Yulia and
Wintner, Shuly",
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/40_Paper.pdf",
abstract = "Parallel corpora are indispensable resources for a variety of multilingual natural language processing tasks. This paper presents a technique for fully automatic construction of constantly growing parallel corpora. We propose a simple and effective dictionary-based algorithm to extract parallel document pairs from a large collection of articles retrieved from the Internet, potentially containing manually translated texts. This algorithm was implemented and tested on Hebrew-English parallel texts. With properly selected thresholds, precision of 100{\%} can be obtained.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tsvetkov-wintner-2010-automatic">
<titleInfo>
<title>Automatic Acquisition of Parallel Corpora from Websites with Dynamic Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuly</namePart>
<namePart type="family">Wintner</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>Parallel corpora are indispensable resources for a variety of multilingual natural language processing tasks. This paper presents a technique for fully automatic construction of constantly growing parallel corpora. We propose a simple and effective dictionary-based algorithm to extract parallel document pairs from a large collection of articles retrieved from the Internet, potentially containing manually translated texts. This algorithm was implemented and tested on Hebrew-English parallel texts. With properly selected thresholds, precision of 100% can be obtained.</abstract>
<identifier type="citekey">tsvetkov-wintner-2010-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/40_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Acquisition of Parallel Corpora from Websites with Dynamic Content
%A Tsvetkov, Yulia
%A Wintner, Shuly
%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 tsvetkov-wintner-2010-automatic
%X Parallel corpora are indispensable resources for a variety of multilingual natural language processing tasks. This paper presents a technique for fully automatic construction of constantly growing parallel corpora. We propose a simple and effective dictionary-based algorithm to extract parallel document pairs from a large collection of articles retrieved from the Internet, potentially containing manually translated texts. This algorithm was implemented and tested on Hebrew-English parallel texts. With properly selected thresholds, precision of 100% can be obtained.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/40_Paper.pdf
Markdown (Informal)
[Automatic Acquisition of Parallel Corpora from Websites with Dynamic Content](http://www.lrec-conf.org/proceedings/lrec2010/pdf/40_Paper.pdf) (Tsvetkov & Wintner, LREC 2010)
ACL