@inproceedings{eiselen-puttkammer-2014-developing,
title = "Developing Text Resources for Ten {S}outh {A}frican Languages",
author = "Eiselen, Roald and
Puttkammer, Martin",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/1151_Paper.pdf",
pages = "3698--3703",
abstract = "The development of linguistic resources for use in natural language processing is of utmost importance for the continued growth of research and development in the field, especially for resource-scarce languages. In this paper we describe the process and challenges of simultaneously developing multiple linguistic resources for ten of the official languages of South Africa. The project focussed on establishing a set of foundational resources that can foster further development of both resources and technologies for the NLP industry in South Africa. The development efforts during the project included creating monolingual unannotated corpora, of which a subset of the corpora for each language was annotated on token, orthographic, morphological and morphosyntactic layers. The annotated subsets includes both development and test sets and were used in the creation of five core-technologies, viz. a tokeniser, sentenciser, lemmatiser, part of speech tagger and morphological decomposer for each language. We report on the quality of these tools for each language and discuss the importance of the resources within the South African context.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eiselen-puttkammer-2014-developing">
<titleInfo>
<title>Developing Text Resources for Ten South African Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roald</namePart>
<namePart type="family">Eiselen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Puttkammer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</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">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The development of linguistic resources for use in natural language processing is of utmost importance for the continued growth of research and development in the field, especially for resource-scarce languages. In this paper we describe the process and challenges of simultaneously developing multiple linguistic resources for ten of the official languages of South Africa. The project focussed on establishing a set of foundational resources that can foster further development of both resources and technologies for the NLP industry in South Africa. The development efforts during the project included creating monolingual unannotated corpora, of which a subset of the corpora for each language was annotated on token, orthographic, morphological and morphosyntactic layers. The annotated subsets includes both development and test sets and were used in the creation of five core-technologies, viz. a tokeniser, sentenciser, lemmatiser, part of speech tagger and morphological decomposer for each language. We report on the quality of these tools for each language and discuss the importance of the resources within the South African context.</abstract>
<identifier type="citekey">eiselen-puttkammer-2014-developing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1151_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3698</start>
<end>3703</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing Text Resources for Ten South African Languages
%A Eiselen, Roald
%A Puttkammer, Martin
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F eiselen-puttkammer-2014-developing
%X The development of linguistic resources for use in natural language processing is of utmost importance for the continued growth of research and development in the field, especially for resource-scarce languages. In this paper we describe the process and challenges of simultaneously developing multiple linguistic resources for ten of the official languages of South Africa. The project focussed on establishing a set of foundational resources that can foster further development of both resources and technologies for the NLP industry in South Africa. The development efforts during the project included creating monolingual unannotated corpora, of which a subset of the corpora for each language was annotated on token, orthographic, morphological and morphosyntactic layers. The annotated subsets includes both development and test sets and were used in the creation of five core-technologies, viz. a tokeniser, sentenciser, lemmatiser, part of speech tagger and morphological decomposer for each language. We report on the quality of these tools for each language and discuss the importance of the resources within the South African context.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1151_Paper.pdf
%P 3698-3703
Markdown (Informal)
[Developing Text Resources for Ten South African Languages](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1151_Paper.pdf) (Eiselen & Puttkammer, LREC 2014)
ACL
- Roald Eiselen and Martin Puttkammer. 2014. Developing Text Resources for Ten South African Languages. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3698–3703, Reykjavik, Iceland. European Language Resources Association (ELRA).