@inproceedings{bayrak-issifu-2022-domain,
title = "Domain-Adapted {BERT}-based Models for Nuanced {A}rabic Dialect Identification and Tweet Sentiment Analysis",
author = "Bayrak, Giyaseddin and
Issifu, Abdul Majeed",
editor = "Bouamor, Houda and
Al-Khalifa, Hend and
Darwish, Kareem and
Rambow, Owen and
Bougares, Fethi and
Abdelali, Ahmed and
Tomeh, Nadi and
Khalifa, Salam and
Zaghouani, Wajdi",
booktitle = "Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wanlp-1.43",
doi = "10.18653/v1/2022.wanlp-1.43",
pages = "425--430",
abstract = "This paper summarizes the solution of the Nuanced Arabic Dialect Identification (NADI) 2022 shared task. It consists of two subtasks: a country-level Arabic Dialect Identification (ADID) and an Arabic Sentiment Analysis (ASA). Our work shows the importance of using domain-adapted models and language-specific pre-processing in NLP task solutions. We implement a simple but strong baseline technique to increase the stability of fine-tuning settings to obtain a good generalization of models. Our best model for the Dialect Identification subtask achieves a Macro F-1 score of 25.54{\%} as an average of both Test-A (33.89{\%}) and Test-B (19.19{\%}) F-1 scores. We also obtained a Macro F-1 score of 74.29{\%} of positive and negative sentiments only, in the Sentiment Analysis task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bayrak-issifu-2022-domain">
<titleInfo>
<title>Domain-Adapted BERT-based Models for Nuanced Arabic Dialect Identification and Tweet Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giyaseddin</namePart>
<namePart type="family">Bayrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdul</namePart>
<namePart type="given">Majeed</namePart>
<namePart type="family">Issifu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)</title>
</titleInfo>
<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">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</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">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">Salam</namePart>
<namePart type="family">Khalifa</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">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper summarizes the solution of the Nuanced Arabic Dialect Identification (NADI) 2022 shared task. It consists of two subtasks: a country-level Arabic Dialect Identification (ADID) and an Arabic Sentiment Analysis (ASA). Our work shows the importance of using domain-adapted models and language-specific pre-processing in NLP task solutions. We implement a simple but strong baseline technique to increase the stability of fine-tuning settings to obtain a good generalization of models. Our best model for the Dialect Identification subtask achieves a Macro F-1 score of 25.54% as an average of both Test-A (33.89%) and Test-B (19.19%) F-1 scores. We also obtained a Macro F-1 score of 74.29% of positive and negative sentiments only, in the Sentiment Analysis task.</abstract>
<identifier type="citekey">bayrak-issifu-2022-domain</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.43</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.43</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>425</start>
<end>430</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain-Adapted BERT-based Models for Nuanced Arabic Dialect Identification and Tweet Sentiment Analysis
%A Bayrak, Giyaseddin
%A Issifu, Abdul Majeed
%Y Bouamor, Houda
%Y Al-Khalifa, Hend
%Y Darwish, Kareem
%Y Rambow, Owen
%Y Bougares, Fethi
%Y Abdelali, Ahmed
%Y Tomeh, Nadi
%Y Khalifa, Salam
%Y Zaghouani, Wajdi
%S Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F bayrak-issifu-2022-domain
%X This paper summarizes the solution of the Nuanced Arabic Dialect Identification (NADI) 2022 shared task. It consists of two subtasks: a country-level Arabic Dialect Identification (ADID) and an Arabic Sentiment Analysis (ASA). Our work shows the importance of using domain-adapted models and language-specific pre-processing in NLP task solutions. We implement a simple but strong baseline technique to increase the stability of fine-tuning settings to obtain a good generalization of models. Our best model for the Dialect Identification subtask achieves a Macro F-1 score of 25.54% as an average of both Test-A (33.89%) and Test-B (19.19%) F-1 scores. We also obtained a Macro F-1 score of 74.29% of positive and negative sentiments only, in the Sentiment Analysis task.
%R 10.18653/v1/2022.wanlp-1.43
%U https://aclanthology.org/2022.wanlp-1.43
%U https://doi.org/10.18653/v1/2022.wanlp-1.43
%P 425-430
Markdown (Informal)
[Domain-Adapted BERT-based Models for Nuanced Arabic Dialect Identification and Tweet Sentiment Analysis](https://aclanthology.org/2022.wanlp-1.43) (Bayrak & Issifu, WANLP 2022)
ACL