@inproceedings{jawaid-etal-2014-tagged,
title = "A Tagged Corpus and a Tagger for {U}rdu",
author = "Jawaid, Bushra and
Kamran, Amir and
Bojar, Ond{\v{r}}ej",
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/544_Paper.pdf",
pages = "2938--2943",
abstract = "In this paper, we describe a release of a sizeable monolingual Urdu corpus automatically tagged with part-of-speech tags. We extend the work of Jawaid and Bojar (2012) who use three different taggers and then apply a voting scheme to disambiguate among the different choices suggested by each tagger. We run this complex ensemble on a large monolingual corpus and release the tagged corpus. Additionally, we use this data to train a single standalone tagger which will hopefully significantly simplify Urdu processing. The standalone tagger obtains the accuracy of 88.74{\%} on test data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jawaid-etal-2014-tagged">
<titleInfo>
<title>A Tagged Corpus and a Tagger for Urdu</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bushra</namePart>
<namePart type="family">Jawaid</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Kamran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</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>In this paper, we describe a release of a sizeable monolingual Urdu corpus automatically tagged with part-of-speech tags. We extend the work of Jawaid and Bojar (2012) who use three different taggers and then apply a voting scheme to disambiguate among the different choices suggested by each tagger. We run this complex ensemble on a large monolingual corpus and release the tagged corpus. Additionally, we use this data to train a single standalone tagger which will hopefully significantly simplify Urdu processing. The standalone tagger obtains the accuracy of 88.74% on test data.</abstract>
<identifier type="citekey">jawaid-etal-2014-tagged</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/544_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2938</start>
<end>2943</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Tagged Corpus and a Tagger for Urdu
%A Jawaid, Bushra
%A Kamran, Amir
%A Bojar, Ondřej
%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 jawaid-etal-2014-tagged
%X In this paper, we describe a release of a sizeable monolingual Urdu corpus automatically tagged with part-of-speech tags. We extend the work of Jawaid and Bojar (2012) who use three different taggers and then apply a voting scheme to disambiguate among the different choices suggested by each tagger. We run this complex ensemble on a large monolingual corpus and release the tagged corpus. Additionally, we use this data to train a single standalone tagger which will hopefully significantly simplify Urdu processing. The standalone tagger obtains the accuracy of 88.74% on test data.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/544_Paper.pdf
%P 2938-2943
Markdown (Informal)
[A Tagged Corpus and a Tagger for Urdu](http://www.lrec-conf.org/proceedings/lrec2014/pdf/544_Paper.pdf) (Jawaid et al., LREC 2014)
ACL
- Bushra Jawaid, Amir Kamran, and Ondřej Bojar. 2014. A Tagged Corpus and a Tagger for Urdu. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2938–2943, Reykjavik, Iceland. European Language Resources Association (ELRA).