@inproceedings{maamouri-etal-2014-developing,
title = "Developing an {E}gyptian {A}rabic Treebank: Impact of Dialectal Morphology on Annotation and Tool Development",
author = "Maamouri, Mohamed and
Bies, Ann and
Kulick, Seth and
Ciul, Michael and
Habash, Nizar 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/1145_Paper.pdf",
pages = "2348--2354",
abstract = "This paper describes the parallel development of an Egyptian Arabic Treebank and a morphological analyzer for Egyptian Arabic (CALIMA). By the very nature of Egyptian Arabic, the data collected is informal, for example Discussion Forum text, which we use for the treebank discussed here. In addition, Egyptian Arabic, like other Arabic dialects, is sufficiently different from Modern Standard Arabic (MSA) that tools and techniques developed for MSA cannot be simply transferred over to work on Egyptian Arabic work. In particular, a morphological analyzer for Egyptian Arabic is needed to mediate between the written text and the segmented, vocalized form used for the syntactic trees. This led to the necessity of a feedback loop between the treebank team and the analyzer team, as improvements in each area were fed to the other. Therefore, by necessity, there needed to be close cooperation between the annotation team and the tool development team, which was to their mutual benefit. Collaboration on this type of challenge, where tools and resources are limited, proved to be remarkably synergistic and opens the way to further fruitful work on Arabic dialects.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maamouri-etal-2014-developing">
<titleInfo>
<title>Developing an Egyptian Arabic Treebank: Impact of Dialectal Morphology on Annotation and Tool Development</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Maamouri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ann</namePart>
<namePart type="family">Bies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seth</namePart>
<namePart type="family">Kulick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Ciul</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">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>This paper describes the parallel development of an Egyptian Arabic Treebank and a morphological analyzer for Egyptian Arabic (CALIMA). By the very nature of Egyptian Arabic, the data collected is informal, for example Discussion Forum text, which we use for the treebank discussed here. In addition, Egyptian Arabic, like other Arabic dialects, is sufficiently different from Modern Standard Arabic (MSA) that tools and techniques developed for MSA cannot be simply transferred over to work on Egyptian Arabic work. In particular, a morphological analyzer for Egyptian Arabic is needed to mediate between the written text and the segmented, vocalized form used for the syntactic trees. This led to the necessity of a feedback loop between the treebank team and the analyzer team, as improvements in each area were fed to the other. Therefore, by necessity, there needed to be close cooperation between the annotation team and the tool development team, which was to their mutual benefit. Collaboration on this type of challenge, where tools and resources are limited, proved to be remarkably synergistic and opens the way to further fruitful work on Arabic dialects.</abstract>
<identifier type="citekey">maamouri-etal-2014-developing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1145_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2348</start>
<end>2354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing an Egyptian Arabic Treebank: Impact of Dialectal Morphology on Annotation and Tool Development
%A Maamouri, Mohamed
%A Bies, Ann
%A Kulick, Seth
%A Ciul, Michael
%A Habash, Nizar
%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 maamouri-etal-2014-developing
%X This paper describes the parallel development of an Egyptian Arabic Treebank and a morphological analyzer for Egyptian Arabic (CALIMA). By the very nature of Egyptian Arabic, the data collected is informal, for example Discussion Forum text, which we use for the treebank discussed here. In addition, Egyptian Arabic, like other Arabic dialects, is sufficiently different from Modern Standard Arabic (MSA) that tools and techniques developed for MSA cannot be simply transferred over to work on Egyptian Arabic work. In particular, a morphological analyzer for Egyptian Arabic is needed to mediate between the written text and the segmented, vocalized form used for the syntactic trees. This led to the necessity of a feedback loop between the treebank team and the analyzer team, as improvements in each area were fed to the other. Therefore, by necessity, there needed to be close cooperation between the annotation team and the tool development team, which was to their mutual benefit. Collaboration on this type of challenge, where tools and resources are limited, proved to be remarkably synergistic and opens the way to further fruitful work on Arabic dialects.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1145_Paper.pdf
%P 2348-2354
Markdown (Informal)
[Developing an Egyptian Arabic Treebank: Impact of Dialectal Morphology on Annotation and Tool Development](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1145_Paper.pdf) (Maamouri et al., LREC 2014)
ACL