@inproceedings{abdel-salam-2022-dialect,
title = "Dialect {\&} Sentiment Identification in Nuanced {A}rabic Tweets Using an Ensemble of Prompt-based, Fine-tuned, and Multitask {BERT}-Based Models",
author = "Abdel-Salam, Reem",
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-1.48",
doi = "10.18653/v1/2022.wanlp-1.48",
pages = "452--457",
abstract = "Dialect Identification is important to improve the performance of various application as translation, speech recognition, etc. In this paper, we present our findings and results in the Nuanced Arabic Dialect Identification Shared Task (NADI 2022) for country-level dialect identification and sentiment identification for dialectical Arabic. The proposed model is an ensemble between fine-tuned BERT-based models and various approaches of prompt-tuning. Our model secured first place on the leaderboard for subtask 1 with an 27.06 F1-macro score, and subtask 2 secured first place with 75.15 F1-PN score. Our findings show that prompt-tuning-based models achieved better performance when compared to fine-tuning and Multi-task based methods. Moreover, using an ensemble of different loss functions might improve model performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abdel-salam-2022-dialect">
<titleInfo>
<title>Dialect & Sentiment Identification in Nuanced Arabic Tweets Using an Ensemble of Prompt-based, Fine-tuned, and Multitask BERT-Based Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Reem</namePart>
<namePart type="family">Abdel-Salam</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>Dialect Identification is important to improve the performance of various application as translation, speech recognition, etc. In this paper, we present our findings and results in the Nuanced Arabic Dialect Identification Shared Task (NADI 2022) for country-level dialect identification and sentiment identification for dialectical Arabic. The proposed model is an ensemble between fine-tuned BERT-based models and various approaches of prompt-tuning. Our model secured first place on the leaderboard for subtask 1 with an 27.06 F1-macro score, and subtask 2 secured first place with 75.15 F1-PN score. Our findings show that prompt-tuning-based models achieved better performance when compared to fine-tuning and Multi-task based methods. Moreover, using an ensemble of different loss functions might improve model performance.</abstract>
<identifier type="citekey">abdel-salam-2022-dialect</identifier>
<identifier type="doi">10.18653/v1/2022.wanlp-1.48</identifier>
<location>
<url>https://aclanthology.org/2022.wanlp-1.48</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>452</start>
<end>457</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialect & Sentiment Identification in Nuanced Arabic Tweets Using an Ensemble of Prompt-based, Fine-tuned, and Multitask BERT-Based Models
%A Abdel-Salam, Reem
%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 abdel-salam-2022-dialect
%X Dialect Identification is important to improve the performance of various application as translation, speech recognition, etc. In this paper, we present our findings and results in the Nuanced Arabic Dialect Identification Shared Task (NADI 2022) for country-level dialect identification and sentiment identification for dialectical Arabic. The proposed model is an ensemble between fine-tuned BERT-based models and various approaches of prompt-tuning. Our model secured first place on the leaderboard for subtask 1 with an 27.06 F1-macro score, and subtask 2 secured first place with 75.15 F1-PN score. Our findings show that prompt-tuning-based models achieved better performance when compared to fine-tuning and Multi-task based methods. Moreover, using an ensemble of different loss functions might improve model performance.
%R 10.18653/v1/2022.wanlp-1.48
%U https://aclanthology.org/2022.wanlp-1.48
%U https://doi.org/10.18653/v1/2022.wanlp-1.48
%P 452-457
Markdown (Informal)
[Dialect & Sentiment Identification in Nuanced Arabic Tweets Using an Ensemble of Prompt-based, Fine-tuned, and Multitask BERT-Based Models](https://aclanthology.org/2022.wanlp-1.48) (Abdel-Salam, WANLP 2022)
ACL