@inproceedings{deshpande-etal-2023-mavericks,
title = "Mavericks at {NADI} 2023 Shared Task: Unravelling Regional Nuances through Dialect Identification using Transformer-based Approach",
author = "Deshpande, Vedant and
Patwardhan, Yash and
Deshpande, Kshitij and
Mangalvedhekar, Sudeep and
Murumkar, Ravindra",
editor = "Sawaf, Hassan and
El-Beltagy, Samhaa and
Zaghouani, Wajdi and
Magdy, Walid and
Abdelali, Ahmed and
Tomeh, Nadi and
Abu Farha, Ibrahim and
Habash, Nizar and
Khalifa, Salam and
Keleg, Amr and
Haddad, Hatem and
Zitouni, Imed and
Mrini, Khalil and
Almatham, Rawan",
booktitle = "Proceedings of ArabicNLP 2023",
month = dec,
year = "2023",
address = "Singapore (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.arabicnlp-1.74/",
doi = "10.18653/v1/2023.arabicnlp-1.74",
pages = "678--682",
abstract = "In this paper, we present our approach for the {\textquotedblleft}Nuanced Arabic Dialect Identification (NADI) Shared Task 2023{\textquotedblright}. We highlight our methodology for subtask 1 which deals with country-level dialect identification. Recognizing dialects plays an instrumental role in enhancing the performance of various downstream NLP tasks such as speech recognition and translation. The task uses the Twitter dataset (TWT-2023) that encompasses 18 dialects for the multi-class classification problem. Numerous transformer-based models, pre-trained on Arabic language, are employed for identifying country-level dialects. We fine-tune these state-of-the-art models on the provided dataset. Ensembling method is leveraged to yield improved performance of the system. We achieved an F1-score of 76.65 (11th rank on leaderboard) on the test dataset."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deshpande-etal-2023-mavericks">
<titleInfo>
<title>Mavericks at NADI 2023 Shared Task: Unravelling Regional Nuances through Dialect Identification using Transformer-based Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vedant</namePart>
<namePart type="family">Deshpande</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="family">Patwardhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kshitij</namePart>
<namePart type="family">Deshpande</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sudeep</namePart>
<namePart type="family">Mangalvedhekar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ravindra</namePart>
<namePart type="family">Murumkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of ArabicNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samhaa</namePart>
<namePart type="family">El-Beltagy</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">Walid</namePart>
<namePart type="family">Magdy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abdelali</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">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salam</namePart>
<namePart type="family">Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amr</namePart>
<namePart type="family">Keleg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hatem</namePart>
<namePart type="family">Haddad</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">Khalil</namePart>
<namePart type="family">Mrini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rawan</namePart>
<namePart type="family">Almatham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present our approach for the “Nuanced Arabic Dialect Identification (NADI) Shared Task 2023”. We highlight our methodology for subtask 1 which deals with country-level dialect identification. Recognizing dialects plays an instrumental role in enhancing the performance of various downstream NLP tasks such as speech recognition and translation. The task uses the Twitter dataset (TWT-2023) that encompasses 18 dialects for the multi-class classification problem. Numerous transformer-based models, pre-trained on Arabic language, are employed for identifying country-level dialects. We fine-tune these state-of-the-art models on the provided dataset. Ensembling method is leveraged to yield improved performance of the system. We achieved an F1-score of 76.65 (11th rank on leaderboard) on the test dataset.</abstract>
<identifier type="citekey">deshpande-etal-2023-mavericks</identifier>
<identifier type="doi">10.18653/v1/2023.arabicnlp-1.74</identifier>
<location>
<url>https://aclanthology.org/2023.arabicnlp-1.74/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>678</start>
<end>682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Mavericks at NADI 2023 Shared Task: Unravelling Regional Nuances through Dialect Identification using Transformer-based Approach
%A Deshpande, Vedant
%A Patwardhan, Yash
%A Deshpande, Kshitij
%A Mangalvedhekar, Sudeep
%A Murumkar, Ravindra
%Y Sawaf, Hassan
%Y El-Beltagy, Samhaa
%Y Zaghouani, Wajdi
%Y Magdy, Walid
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Abu Farha, Ibrahim
%Y Habash, Nizar
%Y Khalifa, Salam
%Y Keleg, Amr
%Y Haddad, Hatem
%Y Zitouni, Imed
%Y Mrini, Khalil
%Y Almatham, Rawan
%S Proceedings of ArabicNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore (Hybrid)
%F deshpande-etal-2023-mavericks
%X In this paper, we present our approach for the “Nuanced Arabic Dialect Identification (NADI) Shared Task 2023”. We highlight our methodology for subtask 1 which deals with country-level dialect identification. Recognizing dialects plays an instrumental role in enhancing the performance of various downstream NLP tasks such as speech recognition and translation. The task uses the Twitter dataset (TWT-2023) that encompasses 18 dialects for the multi-class classification problem. Numerous transformer-based models, pre-trained on Arabic language, are employed for identifying country-level dialects. We fine-tune these state-of-the-art models on the provided dataset. Ensembling method is leveraged to yield improved performance of the system. We achieved an F1-score of 76.65 (11th rank on leaderboard) on the test dataset.
%R 10.18653/v1/2023.arabicnlp-1.74
%U https://aclanthology.org/2023.arabicnlp-1.74/
%U https://doi.org/10.18653/v1/2023.arabicnlp-1.74
%P 678-682
Markdown (Informal)
[Mavericks at NADI 2023 Shared Task: Unravelling Regional Nuances through Dialect Identification using Transformer-based Approach](https://aclanthology.org/2023.arabicnlp-1.74/) (Deshpande et al., ArabicNLP 2023)
ACL