@inproceedings{diab-etal-2014-tharwa,
title = "{T}harwa: A Large Scale Dialectal {A}rabic - {S}tandard {A}rabic - {E}nglish Lexicon",
author = "Diab, Mona and
Al-Badrashiny, Mohamed and
Aminian, Maryam and
Attia, Mohammed and
Elfardy, Heba and
Habash, Nizar and
Hawwari, Abdelati and
Salloum, Wael and
Dasigi, Pradeep and
Eskander, Ramy",
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/1161_Paper.pdf",
pages = "3782--3789",
abstract = "We introduce an electronic three-way lexicon, Tharwa, comprising Dialectal Arabic, Modern Standard Arabic and English correspondents. The paper focuses on Egyptian Arabic as the first pilot dialect for the resource, with plans to expand to other dialects of Arabic in later phases of the project. We describe Tharwas creation process and report on its current status. The lexical entries are augmented with various elements of linguistic information such as POS, gender, rationality, number, and root and pattern information. The lexicon is based on a compilation of information from both monolingual and bilingual existing resources such as paper dictionaries and electronic, corpus-based dictionaries. Multiple levels of quality checks are performed on the output of each step in the creation process. The importance of this lexicon lies in the fact that it is the first resource of its kind bridging multiple variants of Arabic with English. Furthermore, it is a wide coverage lexical resource containing over 73,000 Egyptian entries. Tharwa is publicly available. We believe it will have a significant impact on both Theoretical Linguistics as well as Computational Linguistics research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="diab-etal-2014-tharwa">
<titleInfo>
<title>Tharwa: A Large Scale Dialectal Arabic - Standard Arabic - English Lexicon</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Al-Badrashiny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maryam</namePart>
<namePart type="family">Aminian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="family">Attia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heba</namePart>
<namePart type="family">Elfardy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdelati</namePart>
<namePart type="family">Hawwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wael</namePart>
<namePart type="family">Salloum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pradeep</namePart>
<namePart type="family">Dasigi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramy</namePart>
<namePart type="family">Eskander</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>We introduce an electronic three-way lexicon, Tharwa, comprising Dialectal Arabic, Modern Standard Arabic and English correspondents. The paper focuses on Egyptian Arabic as the first pilot dialect for the resource, with plans to expand to other dialects of Arabic in later phases of the project. We describe Tharwas creation process and report on its current status. The lexical entries are augmented with various elements of linguistic information such as POS, gender, rationality, number, and root and pattern information. The lexicon is based on a compilation of information from both monolingual and bilingual existing resources such as paper dictionaries and electronic, corpus-based dictionaries. Multiple levels of quality checks are performed on the output of each step in the creation process. The importance of this lexicon lies in the fact that it is the first resource of its kind bridging multiple variants of Arabic with English. Furthermore, it is a wide coverage lexical resource containing over 73,000 Egyptian entries. Tharwa is publicly available. We believe it will have a significant impact on both Theoretical Linguistics as well as Computational Linguistics research.</abstract>
<identifier type="citekey">diab-etal-2014-tharwa</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1161_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3782</start>
<end>3789</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tharwa: A Large Scale Dialectal Arabic - Standard Arabic - English Lexicon
%A Diab, Mona
%A Al-Badrashiny, Mohamed
%A Aminian, Maryam
%A Attia, Mohammed
%A Elfardy, Heba
%A Habash, Nizar
%A Hawwari, Abdelati
%A Salloum, Wael
%A Dasigi, Pradeep
%A Eskander, Ramy
%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 diab-etal-2014-tharwa
%X We introduce an electronic three-way lexicon, Tharwa, comprising Dialectal Arabic, Modern Standard Arabic and English correspondents. The paper focuses on Egyptian Arabic as the first pilot dialect for the resource, with plans to expand to other dialects of Arabic in later phases of the project. We describe Tharwas creation process and report on its current status. The lexical entries are augmented with various elements of linguistic information such as POS, gender, rationality, number, and root and pattern information. The lexicon is based on a compilation of information from both monolingual and bilingual existing resources such as paper dictionaries and electronic, corpus-based dictionaries. Multiple levels of quality checks are performed on the output of each step in the creation process. The importance of this lexicon lies in the fact that it is the first resource of its kind bridging multiple variants of Arabic with English. Furthermore, it is a wide coverage lexical resource containing over 73,000 Egyptian entries. Tharwa is publicly available. We believe it will have a significant impact on both Theoretical Linguistics as well as Computational Linguistics research.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1161_Paper.pdf
%P 3782-3789
Markdown (Informal)
[Tharwa: A Large Scale Dialectal Arabic - Standard Arabic - English Lexicon](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1161_Paper.pdf) (Diab et al., LREC 2014)
ACL
- Mona Diab, Mohamed Al-Badrashiny, Maryam Aminian, Mohammed Attia, Heba Elfardy, Nizar Habash, Abdelati Hawwari, Wael Salloum, Pradeep Dasigi, and Ramy Eskander. 2014. Tharwa: A Large Scale Dialectal Arabic - Standard Arabic - English Lexicon. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 3782–3789, Reykjavik, Iceland. European Language Resources Association (ELRA).