@inproceedings{miller-zajic-1998-lexicons,
title = "Lexicons as gold: mining, embellishment and reuse",
author = "Miller, Keith J. and
Zajic, David M.",
editor = "Farwell, David and
Gerber, Laurie and
Hovy, Eduard",
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_43",
pages = "484--493",
abstract = "Given the high labor costs of developing new lexical resources for Machine Translation (MT) and language processing systems, it is desirable to make the most of those resources already in existence. This paper describes the work being carried out on two MT projects that share a common goal: the creation, maintenance and reuse of lexical information. This goal calls into play a range of tasks from dictionary mining of machine-readable dictionaries (MRDs) to the definition of a repository capable of housing this diverse lexical information. This paper outlines the two efforts, focusing on the problems encountered and the intermediate results achieved. While the ultimate goal of the automated processing of on-line resources into multi-purpose lexical repositories is far from being achieved, our experience has shown that there are significant applications that can make use of the partially processed information produced en route. We will describe our experience with two projects, with a focus on one which utilized multiple lexical resources to provide the basis for two natural language processing (NLP) tools: a segmenter and a glosser for Thai. Finally, we make recommendations for future resource development, with a view toward mitigating the difficulties of merging information from diverse sources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="miller-zajic-1998-lexicons">
<titleInfo>
<title>Lexicons as gold: mining, embellishment and reuse</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Zajic</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>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Farwell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laurie</namePart>
<namePart type="family">Gerber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Springer</publisher>
<place>
<placeTerm type="text">Langhorne, PA, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Given the high labor costs of developing new lexical resources for Machine Translation (MT) and language processing systems, it is desirable to make the most of those resources already in existence. This paper describes the work being carried out on two MT projects that share a common goal: the creation, maintenance and reuse of lexical information. This goal calls into play a range of tasks from dictionary mining of machine-readable dictionaries (MRDs) to the definition of a repository capable of housing this diverse lexical information. This paper outlines the two efforts, focusing on the problems encountered and the intermediate results achieved. While the ultimate goal of the automated processing of on-line resources into multi-purpose lexical repositories is far from being achieved, our experience has shown that there are significant applications that can make use of the partially processed information produced en route. We will describe our experience with two projects, with a focus on one which utilized multiple lexical resources to provide the basis for two natural language processing (NLP) tools: a segmenter and a glosser for Thai. Finally, we make recommendations for future resource development, with a view toward mitigating the difficulties of merging information from diverse sources.</abstract>
<identifier type="citekey">miller-zajic-1998-lexicons</identifier>
<location>
<url>https://link.springer.com/chapter/10.1007/3-540-49478-2_43</url>
</location>
<part>
<date>1998-oct 28-31</date>
<extent unit="page">
<start>484</start>
<end>493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lexicons as gold: mining, embellishment and reuse
%A Miller, Keith J.
%A Zajic, David M.
%Y Farwell, David
%Y Gerber, Laurie
%Y Hovy, Eduard
%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 miller-zajic-1998-lexicons
%X Given the high labor costs of developing new lexical resources for Machine Translation (MT) and language processing systems, it is desirable to make the most of those resources already in existence. This paper describes the work being carried out on two MT projects that share a common goal: the creation, maintenance and reuse of lexical information. This goal calls into play a range of tasks from dictionary mining of machine-readable dictionaries (MRDs) to the definition of a repository capable of housing this diverse lexical information. This paper outlines the two efforts, focusing on the problems encountered and the intermediate results achieved. While the ultimate goal of the automated processing of on-line resources into multi-purpose lexical repositories is far from being achieved, our experience has shown that there are significant applications that can make use of the partially processed information produced en route. We will describe our experience with two projects, with a focus on one which utilized multiple lexical resources to provide the basis for two natural language processing (NLP) tools: a segmenter and a glosser for Thai. Finally, we make recommendations for future resource development, with a view toward mitigating the difficulties of merging information from diverse sources.
%U https://link.springer.com/chapter/10.1007/3-540-49478-2_43
%P 484-493
Markdown (Informal)
[Lexicons as gold: mining, embellishment and reuse](https://link.springer.com/chapter/10.1007/3-540-49478-2_43) (Miller & Zajic, AMTA 1998)
ACL
- Keith J. Miller and David M. Zajic. 1998. Lexicons as gold: mining, embellishment and reuse. In Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers, pages 484–493, Langhorne, PA, USA. Springer.