@inproceedings{resnik-1998-parallel,
title = "Parallel strands: a preliminary investigation into mining the Web for bilingual text",
author = "Resnik, Philip",
booktitle = "Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = oct # " 28-31",
year = "1998",
address = "Langhorne, PA, USA",
publisher = "Springer",
url = "https://link.springer.com/chapter/10.1007/3-540-49478-2_7",
pages = "72--82",
abstract = "Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic dificulty of locating parallel texts in all but the most dominant of the world{'}s languages. A parallel corpus resource not yet explored is the World Wide Web, which hosts an abundance of pages in parallel translation, offering a potential solution to some of these problems and unique opportunities of its own. This paper presents the necessary first step in that exploration: a method for automatically finding parallel translated documents on the Web. The technique is conceptually simple, fully language independent, and scalable, and preliminary evaluation results indicate that the method may be accurate enough to apply without human intervention.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="resnik-1998-parallel">
<titleInfo>
<title>Parallel strands: a preliminary investigation into mining the Web for bilingual text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Resnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>1998-oct" 28-31"</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<originInfo>
<publisher>Springer</publisher>
<place>
<placeTerm type="text">Langhorne, PA, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic dificulty of locating parallel texts in all but the most dominant of the world’s languages. A parallel corpus resource not yet explored is the World Wide Web, which hosts an abundance of pages in parallel translation, offering a potential solution to some of these problems and unique opportunities of its own. This paper presents the necessary first step in that exploration: a method for automatically finding parallel translated documents on the Web. The technique is conceptually simple, fully language independent, and scalable, and preliminary evaluation results indicate that the method may be accurate enough to apply without human intervention.</abstract>
<identifier type="citekey">resnik-1998-parallel</identifier>
<location>
<url>https://link.springer.com/chapter/10.1007/3-540-49478-2_7</url>
</location>
<part>
<date>1998-oct" 28-31"</date>
<extent unit="page">
<start>72</start>
<end>82</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Parallel strands: a preliminary investigation into mining the Web for bilingual text
%A Resnik, Philip
%S Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 1998
%8 oct" 28 31"
%I Springer
%C Langhorne, PA, USA
%F resnik-1998-parallel
%X Parallel corpora are a valuable resource for machine translation, but at present their availability and utility is limited by genre- and domain-specificity, licensing restrictions, and the basic dificulty of locating parallel texts in all but the most dominant of the world’s languages. A parallel corpus resource not yet explored is the World Wide Web, which hosts an abundance of pages in parallel translation, offering a potential solution to some of these problems and unique opportunities of its own. This paper presents the necessary first step in that exploration: a method for automatically finding parallel translated documents on the Web. The technique is conceptually simple, fully language independent, and scalable, and preliminary evaluation results indicate that the method may be accurate enough to apply without human intervention.
%U https://link.springer.com/chapter/10.1007/3-540-49478-2_7
%P 72-82
Markdown (Informal)
[Parallel strands: a preliminary investigation into mining the Web for bilingual text](https://link.springer.com/chapter/10.1007/3-540-49478-2_7) (Resnik, AMTA 1998)
ACL