@inproceedings{mohler-mihalcea-2008-babylon,
title = "Babylon Parallel Text Builder: Gathering Parallel Texts for Low-Density Languages",
author = "Mohler, Michael and
Mihalcea, Rada",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/313_paper.pdf",
abstract = "This paper describes Babylon, a system that attempts to overcome the shortage of parallel texts in low-density languages by supplementing existing parallel texts with texts gathered automatically from the Web. In addition to the identification of entire Web pages, we also propose a new feature specifically designed to find parallel text chunks within a single document. Experiments carried out on the Quechua-Spanish language pair show that the system is successful in automatically identifying a significant amount of parallel texts on the Web. Evaluations of a machine translation system trained on this corpus indicate that the Web-gathered parallel texts can supplement manually compiled parallel texts and perform significantly better than the manually compiled texts when tested on other Web-gathered data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohler-mihalcea-2008-babylon">
<titleInfo>
<title>Babylon Parallel Text Builder: Gathering Parallel Texts for Low-Density Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Mohler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes Babylon, a system that attempts to overcome the shortage of parallel texts in low-density languages by supplementing existing parallel texts with texts gathered automatically from the Web. In addition to the identification of entire Web pages, we also propose a new feature specifically designed to find parallel text chunks within a single document. Experiments carried out on the Quechua-Spanish language pair show that the system is successful in automatically identifying a significant amount of parallel texts on the Web. Evaluations of a machine translation system trained on this corpus indicate that the Web-gathered parallel texts can supplement manually compiled parallel texts and perform significantly better than the manually compiled texts when tested on other Web-gathered data.</abstract>
<identifier type="citekey">mohler-mihalcea-2008-babylon</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/313_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Babylon Parallel Text Builder: Gathering Parallel Texts for Low-Density Languages
%A Mohler, Michael
%A Mihalcea, Rada
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F mohler-mihalcea-2008-babylon
%X This paper describes Babylon, a system that attempts to overcome the shortage of parallel texts in low-density languages by supplementing existing parallel texts with texts gathered automatically from the Web. In addition to the identification of entire Web pages, we also propose a new feature specifically designed to find parallel text chunks within a single document. Experiments carried out on the Quechua-Spanish language pair show that the system is successful in automatically identifying a significant amount of parallel texts on the Web. Evaluations of a machine translation system trained on this corpus indicate that the Web-gathered parallel texts can supplement manually compiled parallel texts and perform significantly better than the manually compiled texts when tested on other Web-gathered data.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/313_paper.pdf
Markdown (Informal)
[Babylon Parallel Text Builder: Gathering Parallel Texts for Low-Density Languages](http://www.lrec-conf.org/proceedings/lrec2008/pdf/313_paper.pdf) (Mohler & Mihalcea, LREC 2008)
ACL