@inproceedings{khalifa-etal-2016-large,
title = "A Large Scale Corpus of {G}ulf {A}rabic",
author = "Khalifa, Salam and
Habash, Nizar and
Abdulrahim, Dana and
Hassan, Sara",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1679",
pages = "4282--4289",
abstract = "Most Arabic natural language processing tools and resources are developed to serve Modern Standard Arabic (MSA), which is the official written language in the Arab World. Some Dialectal Arabic varieties, notably Egyptian Arabic, have received some attention lately and have a growing collection of resources that include annotated corpora and morphological analyzers and taggers. Gulf Arabic, however, lags behind in that respect. In this paper, we present the Gumar Corpus, a large-scale corpus of Gulf Arabic consisting of 110 million words from 1,200 forum novels. We annotate the corpus for sub-dialect information at the document level. We also present results of a preliminary study in the morphological annotation of Gulf Arabic which includes developing guidelines for a conventional orthography. The text of the corpus is publicly browsable through a web interface we developed for it.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khalifa-etal-2016-large">
<titleInfo>
<title>A Large Scale Corpus of Gulf Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</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">Dana</namePart>
<namePart type="family">Abdulrahim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Most Arabic natural language processing tools and resources are developed to serve Modern Standard Arabic (MSA), which is the official written language in the Arab World. Some Dialectal Arabic varieties, notably Egyptian Arabic, have received some attention lately and have a growing collection of resources that include annotated corpora and morphological analyzers and taggers. Gulf Arabic, however, lags behind in that respect. In this paper, we present the Gumar Corpus, a large-scale corpus of Gulf Arabic consisting of 110 million words from 1,200 forum novels. We annotate the corpus for sub-dialect information at the document level. We also present results of a preliminary study in the morphological annotation of Gulf Arabic which includes developing guidelines for a conventional orthography. The text of the corpus is publicly browsable through a web interface we developed for it.</abstract>
<identifier type="citekey">khalifa-etal-2016-large</identifier>
<location>
<url>https://aclanthology.org/L16-1679</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4282</start>
<end>4289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large Scale Corpus of Gulf Arabic
%A Khalifa, Salam
%A Habash, Nizar
%A Abdulrahim, Dana
%A Hassan, Sara
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F khalifa-etal-2016-large
%X Most Arabic natural language processing tools and resources are developed to serve Modern Standard Arabic (MSA), which is the official written language in the Arab World. Some Dialectal Arabic varieties, notably Egyptian Arabic, have received some attention lately and have a growing collection of resources that include annotated corpora and morphological analyzers and taggers. Gulf Arabic, however, lags behind in that respect. In this paper, we present the Gumar Corpus, a large-scale corpus of Gulf Arabic consisting of 110 million words from 1,200 forum novels. We annotate the corpus for sub-dialect information at the document level. We also present results of a preliminary study in the morphological annotation of Gulf Arabic which includes developing guidelines for a conventional orthography. The text of the corpus is publicly browsable through a web interface we developed for it.
%U https://aclanthology.org/L16-1679
%P 4282-4289
Markdown (Informal)
[A Large Scale Corpus of Gulf Arabic](https://aclanthology.org/L16-1679) (Khalifa et al., LREC 2016)
ACL
- Salam Khalifa, Nizar Habash, Dana Abdulrahim, and Sara Hassan. 2016. A Large Scale Corpus of Gulf Arabic. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4282–4289, Portorož, Slovenia. European Language Resources Association (ELRA).