@inproceedings{weerasinghe-2002-bootstrapping,
title = "Bootstrapping the lexicon building process for machine translation between {`}new{'} languages",
author = "Weerasinghe, Ruvan",
editor = "Richardson, Stephen D.",
booktitle = "Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = oct # " 8-12",
year = "2002",
address = "Tiburon, USA",
publisher = "Springer",
url = "https://link.springer.com/chapter/10.1007/3-540-45820-4_18",
pages = "177--186",
abstract = "The cumulative effort over the past few decades that have gone into developing linguistic resources for tasks ranging from machine readable dictionaries to translation systems is enormous. Such effort is prohibitively expensive for languages outside the (largely) European family. The possibility of building such resources automatically by accessing electronic corpora of such languages are therefore of great interest to those involved in studying these {`}new{'} - {`}lesser known{'} languages. The main stumbling block to applying these data driven techniques directly is that most of them require large corpora rarely available for such {`}new{'} languages. This paper describes an attempt at setting up a bootstrapping agenda to exploit the scarce corpus resources that may be available at the outset to a researcher concerned with such languages. In particular it reports on results of an experiment to use state-of-the-art data-driven techniques for building linguistic resources for Sinhala - a non-European language with virtually no electronic resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="weerasinghe-2002-bootstrapping">
<titleInfo>
<title>Bootstrapping the lexicon building process for machine translation between ‘new’ languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruvan</namePart>
<namePart type="family">Weerasinghe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2002-oct 8-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Richardson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Springer</publisher>
<place>
<placeTerm type="text">Tiburon, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The cumulative effort over the past few decades that have gone into developing linguistic resources for tasks ranging from machine readable dictionaries to translation systems is enormous. Such effort is prohibitively expensive for languages outside the (largely) European family. The possibility of building such resources automatically by accessing electronic corpora of such languages are therefore of great interest to those involved in studying these ‘new’ - ‘lesser known’ languages. The main stumbling block to applying these data driven techniques directly is that most of them require large corpora rarely available for such ‘new’ languages. This paper describes an attempt at setting up a bootstrapping agenda to exploit the scarce corpus resources that may be available at the outset to a researcher concerned with such languages. In particular it reports on results of an experiment to use state-of-the-art data-driven techniques for building linguistic resources for Sinhala - a non-European language with virtually no electronic resources.</abstract>
<identifier type="citekey">weerasinghe-2002-bootstrapping</identifier>
<location>
<url>https://link.springer.com/chapter/10.1007/3-540-45820-4_18</url>
</location>
<part>
<date>2002-oct 8-12</date>
<extent unit="page">
<start>177</start>
<end>186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bootstrapping the lexicon building process for machine translation between ‘new’ languages
%A Weerasinghe, Ruvan
%Y Richardson, Stephen D.
%S Proceedings of the 5th Conference of the Association for Machine Translation in the Americas: Technical Papers
%D 2002
%8 oct 8 12
%I Springer
%C Tiburon, USA
%F weerasinghe-2002-bootstrapping
%X The cumulative effort over the past few decades that have gone into developing linguistic resources for tasks ranging from machine readable dictionaries to translation systems is enormous. Such effort is prohibitively expensive for languages outside the (largely) European family. The possibility of building such resources automatically by accessing electronic corpora of such languages are therefore of great interest to those involved in studying these ‘new’ - ‘lesser known’ languages. The main stumbling block to applying these data driven techniques directly is that most of them require large corpora rarely available for such ‘new’ languages. This paper describes an attempt at setting up a bootstrapping agenda to exploit the scarce corpus resources that may be available at the outset to a researcher concerned with such languages. In particular it reports on results of an experiment to use state-of-the-art data-driven techniques for building linguistic resources for Sinhala - a non-European language with virtually no electronic resources.
%U https://link.springer.com/chapter/10.1007/3-540-45820-4_18
%P 177-186
Markdown (Informal)
[Bootstrapping the lexicon building process for machine translation between ‘new’ languages](https://link.springer.com/chapter/10.1007/3-540-45820-4_18) (Weerasinghe, AMTA 2002)
ACL