@inproceedings{baldwin-awab-2006-open,
title = "Open Source Corpus Analysis Tools for {M}alay",
author = "Baldwin, Timothy and
Awab, Su{'}ad",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/677_pdf.pdf",
abstract = "Tokenisers, lemmatisers and POS taggers are vital to the linguistic and digital furtherment of any language. In this paper, we present an open source toolkit for Malay incorporating a word and sentence tokeniser, a lemmatiser and a partial POS tagger, based on heavy reuse of pre-existing language resources. We outline the software architecture of each component, and present an evaluation of each over a 26K word sample of Malay text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baldwin-awab-2006-open">
<titleInfo>
<title>Open Source Corpus Analysis Tools for Malay</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Su’ad</namePart>
<namePart type="family">Awab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Tokenisers, lemmatisers and POS taggers are vital to the linguistic and digital furtherment of any language. In this paper, we present an open source toolkit for Malay incorporating a word and sentence tokeniser, a lemmatiser and a partial POS tagger, based on heavy reuse of pre-existing language resources. We outline the software architecture of each component, and present an evaluation of each over a 26K word sample of Malay text.</abstract>
<identifier type="citekey">baldwin-awab-2006-open</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/677_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open Source Corpus Analysis Tools for Malay
%A Baldwin, Timothy
%A Awab, Su’ad
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F baldwin-awab-2006-open
%X Tokenisers, lemmatisers and POS taggers are vital to the linguistic and digital furtherment of any language. In this paper, we present an open source toolkit for Malay incorporating a word and sentence tokeniser, a lemmatiser and a partial POS tagger, based on heavy reuse of pre-existing language resources. We outline the software architecture of each component, and present an evaluation of each over a 26K word sample of Malay text.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/677_pdf.pdf
Markdown (Informal)
[Open Source Corpus Analysis Tools for Malay](http://www.lrec-conf.org/proceedings/lrec2006/pdf/677_pdf.pdf) (Baldwin & Awab, LREC 2006)
ACL
- Timothy Baldwin and Su’ad Awab. 2006. Open Source Corpus Analysis Tools for Malay. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).