@inproceedings{sawalha-etal-2019-construction,
title = "Construction and Annotation of the {J}ordan Comprehensive Contemporary {A}rabic Corpus ({JCCA})",
author = "Sawalha, Majdi and
Alshargi, Faisal and
AlShdaifat, Abdallah and
Yagi, Sane and
Qudah, Mohammad A.",
editor = "El-Hajj, Wassim and
Belguith, Lamia Hadrich and
Bougares, Fethi and
Magdy, Walid and
Zitouni, Imed and
Tomeh, Nadi and
El-Haj, Mahmoud and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Fourth Arabic Natural Language Processing Workshop",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4616",
doi = "10.18653/v1/W19-4616",
pages = "148--157",
abstract = "To compile a modern dictionary that catalogues the words in currency, and to study linguistic patterns in the contemporary language, it is necessary to have a corpus of authentic texts that reflect current usage of the language. Although there are numerous Arabic corpora, none claims to be representative of the language in terms of the combination of geographical region, genre, subject matter, mode, and medium. This paper describes a 100-million-word corpus that takes the British National Corpus (BNC) as a model. The aim of the corpus is to be balanced, annotated, comprehensive, and representative of contemporary Arabic as written and spoken in Arab countries today. It will be different from most others in not being heavily-dominated by the news or in mixing the classical with the modern. In this paper is an outline of the methodology adopted for the design, construction, and annotation of this corpus. DIWAN (Alshargi and Rambow, 2015) was used to annotate a one-million-word snapshot of the corpus. DIWAN is a dialectal word annotation tool, but we upgraded it by adding a new tag-set that is based on traditional Arabic grammar and by adding the roots and morphological patterns of nouns and verbs. Moreover, the corpus we constructed covers the major spoken varieties of Arabic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawalha-etal-2019-construction">
<titleInfo>
<title>Construction and Annotation of the Jordan Comprehensive Contemporary Arabic Corpus (JCCA)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Majdi</namePart>
<namePart type="family">Sawalha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faisal</namePart>
<namePart type="family">Alshargi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdallah</namePart>
<namePart type="family">AlShdaifat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sane</namePart>
<namePart type="family">Yagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Qudah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wassim</namePart>
<namePart type="family">El-Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lamia</namePart>
<namePart type="given">Hadrich</namePart>
<namePart type="family">Belguith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fethi</namePart>
<namePart type="family">Bougares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahmoud</namePart>
<namePart type="family">El-Haj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To compile a modern dictionary that catalogues the words in currency, and to study linguistic patterns in the contemporary language, it is necessary to have a corpus of authentic texts that reflect current usage of the language. Although there are numerous Arabic corpora, none claims to be representative of the language in terms of the combination of geographical region, genre, subject matter, mode, and medium. This paper describes a 100-million-word corpus that takes the British National Corpus (BNC) as a model. The aim of the corpus is to be balanced, annotated, comprehensive, and representative of contemporary Arabic as written and spoken in Arab countries today. It will be different from most others in not being heavily-dominated by the news or in mixing the classical with the modern. In this paper is an outline of the methodology adopted for the design, construction, and annotation of this corpus. DIWAN (Alshargi and Rambow, 2015) was used to annotate a one-million-word snapshot of the corpus. DIWAN is a dialectal word annotation tool, but we upgraded it by adding a new tag-set that is based on traditional Arabic grammar and by adding the roots and morphological patterns of nouns and verbs. Moreover, the corpus we constructed covers the major spoken varieties of Arabic.</abstract>
<identifier type="citekey">sawalha-etal-2019-construction</identifier>
<identifier type="doi">10.18653/v1/W19-4616</identifier>
<location>
<url>https://aclanthology.org/W19-4616</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>148</start>
<end>157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Construction and Annotation of the Jordan Comprehensive Contemporary Arabic Corpus (JCCA)
%A Sawalha, Majdi
%A Alshargi, Faisal
%A AlShdaifat, Abdallah
%A Yagi, Sane
%A Qudah, Mohammad A.
%Y El-Hajj, Wassim
%Y Belguith, Lamia Hadrich
%Y Bougares, Fethi
%Y Magdy, Walid
%Y Zitouni, Imed
%Y Tomeh, Nadi
%Y El-Haj, Mahmoud
%Y Zaghouani, Wajdi
%S Proceedings of the Fourth Arabic Natural Language Processing Workshop
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F sawalha-etal-2019-construction
%X To compile a modern dictionary that catalogues the words in currency, and to study linguistic patterns in the contemporary language, it is necessary to have a corpus of authentic texts that reflect current usage of the language. Although there are numerous Arabic corpora, none claims to be representative of the language in terms of the combination of geographical region, genre, subject matter, mode, and medium. This paper describes a 100-million-word corpus that takes the British National Corpus (BNC) as a model. The aim of the corpus is to be balanced, annotated, comprehensive, and representative of contemporary Arabic as written and spoken in Arab countries today. It will be different from most others in not being heavily-dominated by the news or in mixing the classical with the modern. In this paper is an outline of the methodology adopted for the design, construction, and annotation of this corpus. DIWAN (Alshargi and Rambow, 2015) was used to annotate a one-million-word snapshot of the corpus. DIWAN is a dialectal word annotation tool, but we upgraded it by adding a new tag-set that is based on traditional Arabic grammar and by adding the roots and morphological patterns of nouns and verbs. Moreover, the corpus we constructed covers the major spoken varieties of Arabic.
%R 10.18653/v1/W19-4616
%U https://aclanthology.org/W19-4616
%U https://doi.org/10.18653/v1/W19-4616
%P 148-157
Markdown (Informal)
[Construction and Annotation of the Jordan Comprehensive Contemporary Arabic Corpus (JCCA)](https://aclanthology.org/W19-4616) (Sawalha et al., WANLP 2019)
ACL