@inproceedings{malik-etal-2010-transliterating,
title = "Transliterating {U}rdu for a Broad-Coverage {U}rdu/{H}indi {LFG} Grammar",
author = {Malik, Muhammad Kamran and
Ahmed, Tafseer and
Sulger, Sebastian and
B{\"o}gel, Tina and
Gulzar, Atif and
Raza, Ghulam and
Hussain, Sarmad and
Butt, Miriam},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/194_Paper.pdf",
abstract = "In this paper, we present a system for transliterating the Arabic-based script of Urdu to a Roman transliteration scheme. The system is integrated into a larger system consisting of a morphology module, implemented via finite state technologies, and a computational LFG grammar of Urdu that was developed with the grammar development platform XLE (Crouch et al. 2008). Our long-term goal is to handle Hindi alongside Urdu; the two languages are very similar with respect to syntax and lexicon and hence, one grammar can be used to cover both languages. However, they are not similar concerning the script -- Hindi is written in Devanagari, while Urdu uses an Arabic-based script. By abstracting away to a common Roman transliteration scheme in the respective transliterators, our system can be enabled to handle both languages in parallel. In this paper, we discuss the pipeline architecture of the Urdu-Roman transliterator, mention several linguistic and orthographic issues and present the integration of the transliterator into the LFG parsing system.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="malik-etal-2010-transliterating">
<titleInfo>
<title>Transliterating Urdu for a Broad-Coverage Urdu/Hindi LFG Grammar</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Kamran</namePart>
<namePart type="family">Malik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tafseer</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Sulger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tina</namePart>
<namePart type="family">Bögel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atif</namePart>
<namePart type="family">Gulzar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ghulam</namePart>
<namePart type="family">Raza</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">Miriam</namePart>
<namePart type="family">Butt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a system for transliterating the Arabic-based script of Urdu to a Roman transliteration scheme. The system is integrated into a larger system consisting of a morphology module, implemented via finite state technologies, and a computational LFG grammar of Urdu that was developed with the grammar development platform XLE (Crouch et al. 2008). Our long-term goal is to handle Hindi alongside Urdu; the two languages are very similar with respect to syntax and lexicon and hence, one grammar can be used to cover both languages. However, they are not similar concerning the script – Hindi is written in Devanagari, while Urdu uses an Arabic-based script. By abstracting away to a common Roman transliteration scheme in the respective transliterators, our system can be enabled to handle both languages in parallel. In this paper, we discuss the pipeline architecture of the Urdu-Roman transliterator, mention several linguistic and orthographic issues and present the integration of the transliterator into the LFG parsing system.</abstract>
<identifier type="citekey">malik-etal-2010-transliterating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/194_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transliterating Urdu for a Broad-Coverage Urdu/Hindi LFG Grammar
%A Malik, Muhammad Kamran
%A Ahmed, Tafseer
%A Sulger, Sebastian
%A Bögel, Tina
%A Gulzar, Atif
%A Raza, Ghulam
%A Hussain, Sarmad
%A Butt, Miriam
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F malik-etal-2010-transliterating
%X In this paper, we present a system for transliterating the Arabic-based script of Urdu to a Roman transliteration scheme. The system is integrated into a larger system consisting of a morphology module, implemented via finite state technologies, and a computational LFG grammar of Urdu that was developed with the grammar development platform XLE (Crouch et al. 2008). Our long-term goal is to handle Hindi alongside Urdu; the two languages are very similar with respect to syntax and lexicon and hence, one grammar can be used to cover both languages. However, they are not similar concerning the script – Hindi is written in Devanagari, while Urdu uses an Arabic-based script. By abstracting away to a common Roman transliteration scheme in the respective transliterators, our system can be enabled to handle both languages in parallel. In this paper, we discuss the pipeline architecture of the Urdu-Roman transliterator, mention several linguistic and orthographic issues and present the integration of the transliterator into the LFG parsing system.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/194_Paper.pdf
Markdown (Informal)
[Transliterating Urdu for a Broad-Coverage Urdu/Hindi LFG Grammar](http://www.lrec-conf.org/proceedings/lrec2010/pdf/194_Paper.pdf) (Malik et al., LREC 2010)
ACL
- Muhammad Kamran Malik, Tafseer Ahmed, Sebastian Sulger, Tina Bögel, Atif Gulzar, Ghulam Raza, Sarmad Hussain, and Miriam Butt. 2010. Transliterating Urdu for a Broad-Coverage Urdu/Hindi LFG Grammar. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).