@inproceedings{heid-etal-2006-grammar,
title = "Grammar-based tools for the creation of tagging resources for an unresourced language: the case of {N}orthern {S}otho",
author = "Heid, Ulrich and
Taljard, Elsab{\'e} and
Prinsloo, Danie J.",
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/376_pdf.pdf",
abstract = "We describe an architecture for the parallel construction of a tagger lexicon and an annotated reference corpus for the part-of-speech tagging of Nothern Sotho, a Bantu language of South Africa, for which no tagged resources have been available so far. Our tools make use of grammatical properties (morphological and syntactic) of the language. We use symbolic pretagging, followed by stochastic tagging, an architecture which proves useful not only for the bootstrapping of tagging resources, but also for the tagging of any new text. We discuss the tagset design, the tool architecture and the current state of our ongoing effort.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heid-etal-2006-grammar">
<titleInfo>
<title>Grammar-based tools for the creation of tagging resources for an unresourced language: the case of Northern Sotho</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ulrich</namePart>
<namePart type="family">Heid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elsabé</namePart>
<namePart type="family">Taljard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Danie</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Prinsloo</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>We describe an architecture for the parallel construction of a tagger lexicon and an annotated reference corpus for the part-of-speech tagging of Nothern Sotho, a Bantu language of South Africa, for which no tagged resources have been available so far. Our tools make use of grammatical properties (morphological and syntactic) of the language. We use symbolic pretagging, followed by stochastic tagging, an architecture which proves useful not only for the bootstrapping of tagging resources, but also for the tagging of any new text. We discuss the tagset design, the tool architecture and the current state of our ongoing effort.</abstract>
<identifier type="citekey">heid-etal-2006-grammar</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/376_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grammar-based tools for the creation of tagging resources for an unresourced language: the case of Northern Sotho
%A Heid, Ulrich
%A Taljard, Elsabé
%A Prinsloo, Danie J.
%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 heid-etal-2006-grammar
%X We describe an architecture for the parallel construction of a tagger lexicon and an annotated reference corpus for the part-of-speech tagging of Nothern Sotho, a Bantu language of South Africa, for which no tagged resources have been available so far. Our tools make use of grammatical properties (morphological and syntactic) of the language. We use symbolic pretagging, followed by stochastic tagging, an architecture which proves useful not only for the bootstrapping of tagging resources, but also for the tagging of any new text. We discuss the tagset design, the tool architecture and the current state of our ongoing effort.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/376_pdf.pdf
Markdown (Informal)
[Grammar-based tools for the creation of tagging resources for an unresourced language: the case of Northern Sotho](http://www.lrec-conf.org/proceedings/lrec2006/pdf/376_pdf.pdf) (Heid et al., LREC 2006)
ACL