@inproceedings{oumar-mrini-2022-ahmed,
title = "Ahmed and Khalil at {NADI} 2022: Transfer Learning and Addressing Class Imbalance for {A}rabic Dialect Identification and Sentiment Analysis",
author = "Oumar, Ahmed and
Mrini, Khalil",
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-1.46",
doi = "10.18653/v1/2022.wanlp-1.46",
pages = "442--446",
abstract = "In this paper, we present our findings in the two subtasks of the 2022 NADI shared task. First, in the Arabic dialect identification subtask, we find that there is heavy class imbalance, and propose to address this issue using focal loss. Our experiments with the focusing hyperparameter confirm that focal loss improves performance. Second, in the Arabic tweet sentiment analysis subtask, we deal with a smaller dataset, where text includes both Arabic dialects and Modern Standard Arabic. We propose to use transfer learning from both pre-trained MSA language models and our own model from the first subtask. Our system ranks in the 5th and 7th best spots of the leaderboards of first and second subtasks respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oumar-mrini-2022-ahmed">
<titleInfo>
<title>Ahmed and Khalil at NADI 2022: Transfer Learning and Addressing Class Imbalance for Arabic Dialect Identification and Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Oumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalil</namePart>
<namePart type="family">Mrini</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>In this paper, we present our findings in the two subtasks of the 2022 NADI shared task. First, in the Arabic dialect identification subtask, we find that there is heavy class imbalance, and propose to address this issue using focal loss. Our experiments with the focusing hyperparameter confirm that focal loss improves performance. Second, in the Arabic tweet sentiment analysis subtask, we deal with a smaller dataset, where text includes both Arabic dialects and Modern Standard Arabic. We propose to use transfer learning from both pre-trained MSA language models and our own model from the first subtask. Our system ranks in the 5th and 7th best spots of the leaderboards of first and second subtasks respectively.</abstract>
<identifier type="citekey">oumar-mrini-2022-ahmed</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.46</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.46</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>442</start>
<end>446</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Ahmed and Khalil at NADI 2022: Transfer Learning and Addressing Class Imbalance for Arabic Dialect Identification and Sentiment Analysis
%A Oumar, Ahmed
%A Mrini, Khalil
%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 oumar-mrini-2022-ahmed
%X In this paper, we present our findings in the two subtasks of the 2022 NADI shared task. First, in the Arabic dialect identification subtask, we find that there is heavy class imbalance, and propose to address this issue using focal loss. Our experiments with the focusing hyperparameter confirm that focal loss improves performance. Second, in the Arabic tweet sentiment analysis subtask, we deal with a smaller dataset, where text includes both Arabic dialects and Modern Standard Arabic. We propose to use transfer learning from both pre-trained MSA language models and our own model from the first subtask. Our system ranks in the 5th and 7th best spots of the leaderboards of first and second subtasks respectively.
%R 10.18653/v1/2022.wanlp-1.46
%U https://aclanthology.org/2022.wanlp-1.46
%U https://doi.org/10.18653/v1/2022.wanlp-1.46
%P 442-446
Markdown (Informal)
[Ahmed and Khalil at NADI 2022: Transfer Learning and Addressing Class Imbalance for Arabic Dialect Identification and Sentiment Analysis](https://aclanthology.org/2022.wanlp-1.46) (Oumar & Mrini, WANLP 2022)
ACL