@inproceedings{alkhamissi-etal-2021-adapting,
title = "Adapting {MARBERT} for Improved {A}rabic Dialect Identification: Submission to the {NADI} 2021 Shared Task",
author = "AlKhamissi, Badr and
Gabr, Mohamed and
ElNokrashy, Muhammad and
Essam, Khaled",
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-1.29",
pages = "260--264",
abstract = "In this paper, we tackle the Nuanced Arabic Dialect Identification (NADI) shared task (Abdul-Mageed et al., 2021) and demonstrate state-of-the-art results on all of its four subtasks. Tasks are to identify the geographic origin of short Dialectal (DA) and Modern Standard Arabic (MSA) utterances at the levels of both country and province. Our final model is an ensemble of variants built on top of MARBERT that achieves an F1-score of 34.03{\%} for DA at the country-level development set{---}an improvement of 7.63{\%} from previous work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alkhamissi-etal-2021-adapting">
<titleInfo>
<title>Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Badr</namePart>
<namePart type="family">AlKhamissi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Gabr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="family">ElNokrashy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khaled</namePart>
<namePart type="family">Essam</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>In this paper, we tackle the Nuanced Arabic Dialect Identification (NADI) shared task (Abdul-Mageed et al., 2021) and demonstrate state-of-the-art results on all of its four subtasks. Tasks are to identify the geographic origin of short Dialectal (DA) and Modern Standard Arabic (MSA) utterances at the levels of both country and province. Our final model is an ensemble of variants built on top of MARBERT that achieves an F1-score of 34.03% for DA at the country-level development set—an improvement of 7.63% from previous work.</abstract>
<identifier type="citekey">alkhamissi-etal-2021-adapting</identifier>
<location>
<url>https://aclanthology.org/2021.wanlp-1.29</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>260</start>
<end>264</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task
%A AlKhamissi, Badr
%A Gabr, Mohamed
%A ElNokrashy, Muhammad
%A Essam, Khaled
%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 alkhamissi-etal-2021-adapting
%X In this paper, we tackle the Nuanced Arabic Dialect Identification (NADI) shared task (Abdul-Mageed et al., 2021) and demonstrate state-of-the-art results on all of its four subtasks. Tasks are to identify the geographic origin of short Dialectal (DA) and Modern Standard Arabic (MSA) utterances at the levels of both country and province. Our final model is an ensemble of variants built on top of MARBERT that achieves an F1-score of 34.03% for DA at the country-level development set—an improvement of 7.63% from previous work.
%U https://aclanthology.org/2021.wanlp-1.29
%P 260-264
Markdown (Informal)
[Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task](https://aclanthology.org/2021.wanlp-1.29) (AlKhamissi et al., WANLP 2021)
ACL