@inproceedings{abdelali-etal-2021-qadi,
title = "{QADI}: {A}rabic Dialect Identification in the Wild",
author = "Abdelali, Ahmed and
Mubarak, Hamdy and
Samih, Younes and
Hassan, Sabit and
Darwish, Kareem",
editor = "Habash, Nizar and
Bouamor, Houda and
Hajj, Hazem and
Magdy, Walid and
Zaghouani, Wajdi and
Bougares, Fethi and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Touileb, Samia",
booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
month = apr,
year = "2021",
address = "Kyiv, Ukraine (Virtual)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.wanlp-1.1",
pages = "1--10",
abstract = "Proper dialect identification is important for a variety of Arabic NLP applications. In this paper, we present a method for rapidly constructing a tweet dataset containing a wide range of country-level Arabic dialects {---}covering 18 different countries in the Middle East and North Africa region. Our method relies on applying multiple filters to identify users who belong to different countries based on their account descriptions and to eliminate tweets that either write mainly in Modern Standard Arabic or mostly use vulgar language. The resultant dataset contains 540k tweets from 2,525 users who are evenly distributed across 18 Arab countries. Using intrinsic evaluation, we show that the labels of a set of randomly selected tweets are 91.5{\%} accurate. For extrinsic evaluation, we are able to build effective country level dialect identification on tweets with a macro-averaged F1-score of 60.6{\%} across 18 classes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdelali-etal-2021-qadi">
<titleInfo>
<title>QADI: Arabic Dialect Identification in the Wild</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younes</namePart>
<namePart type="family">Samih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabit</namePart>
<namePart type="family">Hassan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Arabic Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hazem</namePart>
<namePart type="family">Hajj</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">Wajdi</namePart>
<namePart type="family">Zaghouani</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">Nadi</namePart>
<namePart type="family">Tomeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Touileb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv, Ukraine (Virtual)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Proper dialect identification is important for a variety of Arabic NLP applications. In this paper, we present a method for rapidly constructing a tweet dataset containing a wide range of country-level Arabic dialects —covering 18 different countries in the Middle East and North Africa region. Our method relies on applying multiple filters to identify users who belong to different countries based on their account descriptions and to eliminate tweets that either write mainly in Modern Standard Arabic or mostly use vulgar language. The resultant dataset contains 540k tweets from 2,525 users who are evenly distributed across 18 Arab countries. Using intrinsic evaluation, we show that the labels of a set of randomly selected tweets are 91.5% accurate. For extrinsic evaluation, we are able to build effective country level dialect identification on tweets with a macro-averaged F1-score of 60.6% across 18 classes.</abstract>
<identifier type="citekey">abdelali-etal-2021-qadi</identifier>
<location>
<url>https://aclanthology.org/2021.wanlp-1.1</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QADI: Arabic Dialect Identification in the Wild
%A Abdelali, Ahmed
%A Mubarak, Hamdy
%A Samih, Younes
%A Hassan, Sabit
%A Darwish, Kareem
%Y Habash, Nizar
%Y Bouamor, Houda
%Y Hajj, Hazem
%Y Magdy, Walid
%Y Zaghouani, Wajdi
%Y Bougares, Fethi
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Touileb, Samia
%S Proceedings of the Sixth Arabic Natural Language Processing Workshop
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv, Ukraine (Virtual)
%F abdelali-etal-2021-qadi
%X Proper dialect identification is important for a variety of Arabic NLP applications. In this paper, we present a method for rapidly constructing a tweet dataset containing a wide range of country-level Arabic dialects —covering 18 different countries in the Middle East and North Africa region. Our method relies on applying multiple filters to identify users who belong to different countries based on their account descriptions and to eliminate tweets that either write mainly in Modern Standard Arabic or mostly use vulgar language. The resultant dataset contains 540k tweets from 2,525 users who are evenly distributed across 18 Arab countries. Using intrinsic evaluation, we show that the labels of a set of randomly selected tweets are 91.5% accurate. For extrinsic evaluation, we are able to build effective country level dialect identification on tweets with a macro-averaged F1-score of 60.6% across 18 classes.
%U https://aclanthology.org/2021.wanlp-1.1
%P 1-10
Markdown (Informal)
[QADI: Arabic Dialect Identification in the Wild](https://aclanthology.org/2021.wanlp-1.1) (Abdelali et al., WANLP 2021)
ACL
- Ahmed Abdelali, Hamdy Mubarak, Younes Samih, Sabit Hassan, and Kareem Darwish. 2021. QADI: Arabic Dialect Identification in the Wild. In Proceedings of the Sixth Arabic Natural Language Processing Workshop, pages 1–10, Kyiv, Ukraine (Virtual). Association for Computational Linguistics.