@inproceedings{gasser-2010-expanding,
title = "Expanding the Lexicon for a Resource-Poor Language Using a Morphological Analyzer and a Web Crawler",
author = "Gasser, Michael",
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/926_Paper.pdf",
abstract = "Resource-poor languages may suffer from a lack of any of the basic resources that are fundamental to computational linguistics, including an adequate digital lexicon. Given the relatively small corpus of texts that exists for such languages, extending the lexicon presents a challenge. Languages with complex morphology present a special case, however, because individual words in these languages provide a great deal of information about the grammatical properties of the roots that they are based on. Given a morphological analyzer, it is even possible to extract novel roots from words. In this paper, we look at the case of Tigrinya, a Semitic language with limited lexical resources for which a morphological analyzer is available. It is shown that this analyzer applied to the list of more than 200,000 Tigrinya words that is extracted by a web crawler can extend the lexicon in two ways, by adding new roots and by inferring some of the derivational constraints that apply to known roots.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gasser-2010-expanding">
<titleInfo>
<title>Expanding the Lexicon for a Resource-Poor Language Using a Morphological Analyzer and a Web Crawler</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gasser</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>Resource-poor languages may suffer from a lack of any of the basic resources that are fundamental to computational linguistics, including an adequate digital lexicon. Given the relatively small corpus of texts that exists for such languages, extending the lexicon presents a challenge. Languages with complex morphology present a special case, however, because individual words in these languages provide a great deal of information about the grammatical properties of the roots that they are based on. Given a morphological analyzer, it is even possible to extract novel roots from words. In this paper, we look at the case of Tigrinya, a Semitic language with limited lexical resources for which a morphological analyzer is available. It is shown that this analyzer applied to the list of more than 200,000 Tigrinya words that is extracted by a web crawler can extend the lexicon in two ways, by adding new roots and by inferring some of the derivational constraints that apply to known roots.</abstract>
<identifier type="citekey">gasser-2010-expanding</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Expanding the Lexicon for a Resource-Poor Language Using a Morphological Analyzer and a Web Crawler
%A Gasser, Michael
%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 gasser-2010-expanding
%X Resource-poor languages may suffer from a lack of any of the basic resources that are fundamental to computational linguistics, including an adequate digital lexicon. Given the relatively small corpus of texts that exists for such languages, extending the lexicon presents a challenge. Languages with complex morphology present a special case, however, because individual words in these languages provide a great deal of information about the grammatical properties of the roots that they are based on. Given a morphological analyzer, it is even possible to extract novel roots from words. In this paper, we look at the case of Tigrinya, a Semitic language with limited lexical resources for which a morphological analyzer is available. It is shown that this analyzer applied to the list of more than 200,000 Tigrinya words that is extracted by a web crawler can extend the lexicon in two ways, by adding new roots and by inferring some of the derivational constraints that apply to known roots.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf
Markdown (Informal)
[Expanding the Lexicon for a Resource-Poor Language Using a Morphological Analyzer and a Web Crawler](http://www.lrec-conf.org/proceedings/lrec2010/pdf/926_Paper.pdf) (Gasser, LREC 2010)
ACL