@inproceedings{abdulrahim-etal-2022-bahrain,
title = "The {B}ahrain Corpus: A Multi-genre Corpus of Bahraini {A}rabic",
author = "Abdulrahim, Dana and
Inoue, Go and
Shamsan, Latifa and
Khalifa, Salam and
Habash, Nizar",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.251",
pages = "2345--2352",
abstract = "In recent years, the focus on developing natural language processing (NLP) tools for Arabic has shifted from Modern Standard Arabic to various Arabic dialects. Various corpora of various sizes and representing different genres, have been created for a number of Arabic dialects. As far as Gulf Arabic is concerned, Gumar Corpus (Khalifa et al., 2016) is the largest corpus, to date, that includes data representing the dialectal Arabic of the six Gulf Cooperation Council countries (Bahrain, Kuwait, Saudi Arabia, Qatar, United Arab Emirates, and Oman), particularly in the genre of {``}online forum novels{''}. In this paper, we present the Bahrain Corpus. Our objective is to create a specialized corpus of the Bahraini Arabic dialect, which includes written texts as well as transcripts of audio files, belonging to a different genre (folktales, comedy shows, plays, cooking shows, etc.). The corpus comprises 620K words, carefully curated. We provide automatic morphological annotations of the full corpus using state-of-the-art morphosyntactic disambiguation for Gulf Arabic. We validate the quality of the annotations on a 7.6K word sample. We plan to make the annotated sample as well as the full corpus publicly available to support researchers interested in Arabic NLP.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdulrahim-etal-2022-bahrain">
<titleInfo>
<title>The Bahrain Corpus: A Multi-genre Corpus of Bahraini Arabic</title>
</titleInfo>
<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">Go</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Latifa</namePart>
<namePart type="family">Shamsan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</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">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, the focus on developing natural language processing (NLP) tools for Arabic has shifted from Modern Standard Arabic to various Arabic dialects. Various corpora of various sizes and representing different genres, have been created for a number of Arabic dialects. As far as Gulf Arabic is concerned, Gumar Corpus (Khalifa et al., 2016) is the largest corpus, to date, that includes data representing the dialectal Arabic of the six Gulf Cooperation Council countries (Bahrain, Kuwait, Saudi Arabia, Qatar, United Arab Emirates, and Oman), particularly in the genre of “online forum novels”. In this paper, we present the Bahrain Corpus. Our objective is to create a specialized corpus of the Bahraini Arabic dialect, which includes written texts as well as transcripts of audio files, belonging to a different genre (folktales, comedy shows, plays, cooking shows, etc.). The corpus comprises 620K words, carefully curated. We provide automatic morphological annotations of the full corpus using state-of-the-art morphosyntactic disambiguation for Gulf Arabic. We validate the quality of the annotations on a 7.6K word sample. We plan to make the annotated sample as well as the full corpus publicly available to support researchers interested in Arabic NLP.</abstract>
<identifier type="citekey">abdulrahim-etal-2022-bahrain</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.251</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2345</start>
<end>2352</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Bahrain Corpus: A Multi-genre Corpus of Bahraini Arabic
%A Abdulrahim, Dana
%A Inoue, Go
%A Shamsan, Latifa
%A Khalifa, Salam
%A Habash, Nizar
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F abdulrahim-etal-2022-bahrain
%X In recent years, the focus on developing natural language processing (NLP) tools for Arabic has shifted from Modern Standard Arabic to various Arabic dialects. Various corpora of various sizes and representing different genres, have been created for a number of Arabic dialects. As far as Gulf Arabic is concerned, Gumar Corpus (Khalifa et al., 2016) is the largest corpus, to date, that includes data representing the dialectal Arabic of the six Gulf Cooperation Council countries (Bahrain, Kuwait, Saudi Arabia, Qatar, United Arab Emirates, and Oman), particularly in the genre of “online forum novels”. In this paper, we present the Bahrain Corpus. Our objective is to create a specialized corpus of the Bahraini Arabic dialect, which includes written texts as well as transcripts of audio files, belonging to a different genre (folktales, comedy shows, plays, cooking shows, etc.). The corpus comprises 620K words, carefully curated. We provide automatic morphological annotations of the full corpus using state-of-the-art morphosyntactic disambiguation for Gulf Arabic. We validate the quality of the annotations on a 7.6K word sample. We plan to make the annotated sample as well as the full corpus publicly available to support researchers interested in Arabic NLP.
%U https://aclanthology.org/2022.lrec-1.251
%P 2345-2352
Markdown (Informal)
[The Bahrain Corpus: A Multi-genre Corpus of Bahraini Arabic](https://aclanthology.org/2022.lrec-1.251) (Abdulrahim et al., LREC 2022)
ACL
- Dana Abdulrahim, Go Inoue, Latifa Shamsan, Salam Khalifa, and Nizar Habash. 2022. The Bahrain Corpus: A Multi-genre Corpus of Bahraini Arabic. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 2345–2352, Marseille, France. European Language Resources Association.