@inproceedings{alshargi-etal-2019-morphologically,
title = "Morphologically Annotated Corpora for Seven {A}rabic Dialects: {T}aizi, {S}anaani, {N}ajdi, {J}ordanian, {S}yrian, {I}raqi and {M}oroccan",
author = "Alshargi, Faisal and
Dibas, Shahd and
Alkhereyf, Sakhar and
Faraj, Reem and
Abdulkareem, Basmah and
Yagi, Sane and
Kacha, Ouafaa and
Habash, Nizar and
Rambow, Owen",
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/W19-4615",
doi = "10.18653/v1/W19-4615",
pages = "137--147",
abstract = "We present a collection of morphologically annotated corpora for seven Arabic dialects: Taizi Yemeni, Sanaani Yemeni, Najdi, Jordanian, Syrian, Iraqi and Moroccan Arabic. The corpora collectively cover over 200,000 words, and are all manually annotated in a common set of standards for orthography, diacritized lemmas, tokenization, morphological units and English glosses. These corpora will be publicly available to serve as benchmarks for training and evaluating systems for Arabic dialect morphological analysis and disambiguation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alshargi-etal-2019-morphologically">
<titleInfo>
<title>Morphologically Annotated Corpora for Seven Arabic Dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Iraqi and Moroccan</title>
</titleInfo>
<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">Shahd</namePart>
<namePart type="family">Dibas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakhar</namePart>
<namePart type="family">Alkhereyf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Faraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Basmah</namePart>
<namePart type="family">Abdulkareem</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">Ouafaa</namePart>
<namePart type="family">Kacha</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">Owen</namePart>
<namePart type="family">Rambow</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>We present a collection of morphologically annotated corpora for seven Arabic dialects: Taizi Yemeni, Sanaani Yemeni, Najdi, Jordanian, Syrian, Iraqi and Moroccan Arabic. The corpora collectively cover over 200,000 words, and are all manually annotated in a common set of standards for orthography, diacritized lemmas, tokenization, morphological units and English glosses. These corpora will be publicly available to serve as benchmarks for training and evaluating systems for Arabic dialect morphological analysis and disambiguation.</abstract>
<identifier type="citekey">alshargi-etal-2019-morphologically</identifier>
<identifier type="doi">10.18653/v1/W19-4615</identifier>
<location>
<url>https://aclanthology.org/W19-4615</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>137</start>
<end>147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Morphologically Annotated Corpora for Seven Arabic Dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Iraqi and Moroccan
%A Alshargi, Faisal
%A Dibas, Shahd
%A Alkhereyf, Sakhar
%A Faraj, Reem
%A Abdulkareem, Basmah
%A Yagi, Sane
%A Kacha, Ouafaa
%A Habash, Nizar
%A Rambow, Owen
%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 alshargi-etal-2019-morphologically
%X We present a collection of morphologically annotated corpora for seven Arabic dialects: Taizi Yemeni, Sanaani Yemeni, Najdi, Jordanian, Syrian, Iraqi and Moroccan Arabic. The corpora collectively cover over 200,000 words, and are all manually annotated in a common set of standards for orthography, diacritized lemmas, tokenization, morphological units and English glosses. These corpora will be publicly available to serve as benchmarks for training and evaluating systems for Arabic dialect morphological analysis and disambiguation.
%R 10.18653/v1/W19-4615
%U https://aclanthology.org/W19-4615
%U https://doi.org/10.18653/v1/W19-4615
%P 137-147
Markdown (Informal)
[Morphologically Annotated Corpora for Seven Arabic Dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Iraqi and Moroccan](https://aclanthology.org/W19-4615) (Alshargi et al., WANLP 2019)
ACL
- Faisal Alshargi, Shahd Dibas, Sakhar Alkhereyf, Reem Faraj, Basmah Abdulkareem, Sane Yagi, Ouafaa Kacha, Nizar Habash, and Owen Rambow. 2019. Morphologically Annotated Corpora for Seven Arabic Dialects: Taizi, Sanaani, Najdi, Jordanian, Syrian, Iraqi and Moroccan. In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 137–147, Florence, Italy. Association for Computational Linguistics.