@inproceedings{abu-farha-magdy-2021-benchmarking,
title = "Benchmarking Transformer-based Language Models for {A}rabic Sentiment and Sarcasm Detection",
author = "Abu Farha, Ibrahim and
Magdy, Walid",
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-1.3/",
pages = "21--31",
abstract = "The introduction of transformer-based language models has been a revolutionary step for natural language processing (NLP) research. These models, such as BERT, GPT and ELECTRA, led to state-of-the-art performance in many NLP tasks. Most of these models were initially developed for English and other languages followed later. Recently, several Arabic-specific models started emerging. However, there are limited direct comparisons between these models. In this paper, we evaluate the performance of 24 of these models on Arabic sentiment and sarcasm detection. Our results show that the models achieving the best performance are those that are trained on only Arabic data, including dialectal Arabic, and use a larger number of parameters, such as the recently released MARBERT. However, we noticed that AraELECTRA is one of the top performing models while being much more efficient in its computational cost. Finally, the experiments on AraGPT2 variants showed low performance compared to BERT models, which indicates that it might not be suitable for classification tasks."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abu-farha-magdy-2021-benchmarking">
<titleInfo>
<title>Benchmarking Transformer-based Language Models for Arabic Sentiment and Sarcasm Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibrahim</namePart>
<namePart type="family">Abu Farha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Walid</namePart>
<namePart type="family">Magdy</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>The introduction of transformer-based language models has been a revolutionary step for natural language processing (NLP) research. These models, such as BERT, GPT and ELECTRA, led to state-of-the-art performance in many NLP tasks. Most of these models were initially developed for English and other languages followed later. Recently, several Arabic-specific models started emerging. However, there are limited direct comparisons between these models. In this paper, we evaluate the performance of 24 of these models on Arabic sentiment and sarcasm detection. Our results show that the models achieving the best performance are those that are trained on only Arabic data, including dialectal Arabic, and use a larger number of parameters, such as the recently released MARBERT. However, we noticed that AraELECTRA is one of the top performing models while being much more efficient in its computational cost. Finally, the experiments on AraGPT2 variants showed low performance compared to BERT models, which indicates that it might not be suitable for classification tasks.</abstract>
<identifier type="citekey">abu-farha-magdy-2021-benchmarking</identifier>
<location>
<url>https://aclanthology.org/2021.wanlp-1.3/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>21</start>
<end>31</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Transformer-based Language Models for Arabic Sentiment and Sarcasm Detection
%A Abu Farha, Ibrahim
%A Magdy, Walid
%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 abu-farha-magdy-2021-benchmarking
%X The introduction of transformer-based language models has been a revolutionary step for natural language processing (NLP) research. These models, such as BERT, GPT and ELECTRA, led to state-of-the-art performance in many NLP tasks. Most of these models were initially developed for English and other languages followed later. Recently, several Arabic-specific models started emerging. However, there are limited direct comparisons between these models. In this paper, we evaluate the performance of 24 of these models on Arabic sentiment and sarcasm detection. Our results show that the models achieving the best performance are those that are trained on only Arabic data, including dialectal Arabic, and use a larger number of parameters, such as the recently released MARBERT. However, we noticed that AraELECTRA is one of the top performing models while being much more efficient in its computational cost. Finally, the experiments on AraGPT2 variants showed low performance compared to BERT models, which indicates that it might not be suitable for classification tasks.
%U https://aclanthology.org/2021.wanlp-1.3/
%P 21-31
Markdown (Informal)
[Benchmarking Transformer-based Language Models for Arabic Sentiment and Sarcasm Detection](https://aclanthology.org/2021.wanlp-1.3/) (Abu Farha & Magdy, WANLP 2021)
ACL