@inproceedings{urooj-etal-2014-cle,
title = "The {CLE} {U}rdu {POS} Tagset",
author = "Urooj, Saba and
Hussain, Sarmad and
Mustafa, Asad and
Parveen, Rahila and
Adeeba, Farah and
Ahmed Khan, Tafseer and
Butt, Miriam and
Hautli, Annette",
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/275_Paper.pdf",
pages = "2920--2925",
abstract = "The paper presents a design schema and details of a new Urdu POS tagset. This tagset is designed due to challenges encountered in working with existing tagsets for Urdu. It uses tags that judiciously incorporate information about special morpho-syntactic categories found in Urdu. With respect to the overall naming schema and the basic divisions, the tagset draws on the Penn Treebank and a Common Tagset for Indian Languages. The resulting CLE Urdu POS Tagset consists of 12 major categories with subdivisions, resulting in 32 tags. The tagset has been used to tag 100k words of the CLE Urdu Digest Corpus, giving a tagging accuracy of 96.8{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="urooj-etal-2014-cle">
<titleInfo>
<title>The CLE Urdu POS Tagset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saba</namePart>
<namePart type="family">Urooj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarmad</namePart>
<namePart type="family">Hussain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asad</namePart>
<namePart type="family">Mustafa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahila</namePart>
<namePart type="family">Parveen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farah</namePart>
<namePart type="family">Adeeba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tafseer</namePart>
<namePart type="family">Ahmed Khan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Butt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Hautli</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 paper presents a design schema and details of a new Urdu POS tagset. This tagset is designed due to challenges encountered in working with existing tagsets for Urdu. It uses tags that judiciously incorporate information about special morpho-syntactic categories found in Urdu. With respect to the overall naming schema and the basic divisions, the tagset draws on the Penn Treebank and a Common Tagset for Indian Languages. The resulting CLE Urdu POS Tagset consists of 12 major categories with subdivisions, resulting in 32 tags. The tagset has been used to tag 100k words of the CLE Urdu Digest Corpus, giving a tagging accuracy of 96.8%.</abstract>
<identifier type="citekey">urooj-etal-2014-cle</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/275_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2920</start>
<end>2925</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The CLE Urdu POS Tagset
%A Urooj, Saba
%A Hussain, Sarmad
%A Mustafa, Asad
%A Parveen, Rahila
%A Adeeba, Farah
%A Ahmed Khan, Tafseer
%A Butt, Miriam
%A Hautli, Annette
%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 urooj-etal-2014-cle
%X The paper presents a design schema and details of a new Urdu POS tagset. This tagset is designed due to challenges encountered in working with existing tagsets for Urdu. It uses tags that judiciously incorporate information about special morpho-syntactic categories found in Urdu. With respect to the overall naming schema and the basic divisions, the tagset draws on the Penn Treebank and a Common Tagset for Indian Languages. The resulting CLE Urdu POS Tagset consists of 12 major categories with subdivisions, resulting in 32 tags. The tagset has been used to tag 100k words of the CLE Urdu Digest Corpus, giving a tagging accuracy of 96.8%.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/275_Paper.pdf
%P 2920-2925
Markdown (Informal)
[The CLE Urdu POS Tagset](http://www.lrec-conf.org/proceedings/lrec2014/pdf/275_Paper.pdf) (Urooj et al., LREC 2014)
ACL
- Saba Urooj, Sarmad Hussain, Asad Mustafa, Rahila Parveen, Farah Adeeba, Tafseer Ahmed Khan, Miriam Butt, and Annette Hautli. 2014. The CLE Urdu POS Tagset. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2920–2925, Reykjavik, Iceland. European Language Resources Association (ELRA).