@inproceedings{mostefa-etal-2012-new,
title = "New language resources for the {P}ashto language",
author = "Mostefa, Djamel and
Choukri, Khalid and
Brunessaux, Sylvie and
Boudahmane, Karim",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/824_Paper.pdf",
pages = "2917--2922",
abstract = "This paper reports on the development of new language resources for the Pashto language, a very low-resource language spoken in Afghanistan and Pakistan. In the scope of a multilingual data collection project, three large corpora are collected for Pashto. Firstly a monolingual text corpus of 100 million words is produced. Secondly a 100 hours speech database is recorded and manually transcribed. Finally a bilingual Pashto-French parallel corpus of around 2 million is produced by translating Pashto texts into French. These resources will be used to develop Human Language Technology systems for Pashto with a special focus on Machine Translation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mostefa-etal-2012-new">
<titleInfo>
<title>New language resources for the Pashto language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Djamel</namePart>
<namePart type="family">Mostefa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvie</namePart>
<namePart type="family">Brunessaux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karim</namePart>
<namePart type="family">Boudahmane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper reports on the development of new language resources for the Pashto language, a very low-resource language spoken in Afghanistan and Pakistan. In the scope of a multilingual data collection project, three large corpora are collected for Pashto. Firstly a monolingual text corpus of 100 million words is produced. Secondly a 100 hours speech database is recorded and manually transcribed. Finally a bilingual Pashto-French parallel corpus of around 2 million is produced by translating Pashto texts into French. These resources will be used to develop Human Language Technology systems for Pashto with a special focus on Machine Translation.</abstract>
<identifier type="citekey">mostefa-etal-2012-new</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/824_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2917</start>
<end>2922</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New language resources for the Pashto language
%A Mostefa, Djamel
%A Choukri, Khalid
%A Brunessaux, Sylvie
%A Boudahmane, Karim
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F mostefa-etal-2012-new
%X This paper reports on the development of new language resources for the Pashto language, a very low-resource language spoken in Afghanistan and Pakistan. In the scope of a multilingual data collection project, three large corpora are collected for Pashto. Firstly a monolingual text corpus of 100 million words is produced. Secondly a 100 hours speech database is recorded and manually transcribed. Finally a bilingual Pashto-French parallel corpus of around 2 million is produced by translating Pashto texts into French. These resources will be used to develop Human Language Technology systems for Pashto with a special focus on Machine Translation.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/824_Paper.pdf
%P 2917-2922
Markdown (Informal)
[New language resources for the Pashto language](http://www.lrec-conf.org/proceedings/lrec2012/pdf/824_Paper.pdf) (Mostefa et al., LREC 2012)
ACL
- Djamel Mostefa, Khalid Choukri, Sylvie Brunessaux, and Karim Boudahmane. 2012. New language resources for the Pashto language. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2917–2922, Istanbul, Turkey. European Language Resources Association (ELRA).