@inproceedings{mohamed-kamr-mohamed-2022-akabert,
title = "aka{BERT} at {S}em{E}val-2022 Task 6: An Ensemble Transformer-based Model for {A}rabic Sarcasm Detection",
author = "Mohamed Kamr, Abdulrahman and
Mohamed, Ensaf",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.124/",
doi = "10.18653/v1/2022.semeval-1.124",
pages = "885--890",
abstract = "Due to the widespread usage of social media sites and the enormous number of users who utilize irony implicit words in most of their tweets and posts, it has become necessary to detect sarcasm, which strongly influences understanding and analyzing the crowd`s opinions. Detecting sarcasm is difficult due to the nature of sarcastic tweets, which vary based on the topic, region, the user`s attitude, culture, terminologies, and other criteria. In addition to these difficulties, detecting sarcasm in Arabic has its challenges due to its complexities, such as being morphologically rich, having many different dialects, and having low resources. In this research, we present our submission of (iSarcasmEval) sub-task A of the shared task on SemEval 2022. In Sub-task A; we determine whether the tweets are sarcastic or non-sarcastic. We implemented different approaches based on Transformers. First, we fine-tuned the AraBERT, MARABERT, and AraELECTRA. One of the challenges that faced us was that the data was not balanced. Non-sarcastic data is much more than sarcastic. We used data augmentation techniques to balance the two classes, significantly affecting the performance. The performance F1 score of the three models was 87{\%}, 90{\%}, and 91{\%}, respectively. Then we boosted the three models by developing an ensemble model based on hard voting. The final performance F1 Score was 93{\%}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mohamed-kamr-mohamed-2022-akabert">
<titleInfo>
<title>akaBERT at SemEval-2022 Task 6: An Ensemble Transformer-based Model for Arabic Sarcasm Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdulrahman</namePart>
<namePart type="family">Mohamed Kamr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ensaf</namePart>
<namePart type="family">Mohamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Due to the widespread usage of social media sites and the enormous number of users who utilize irony implicit words in most of their tweets and posts, it has become necessary to detect sarcasm, which strongly influences understanding and analyzing the crowd‘s opinions. Detecting sarcasm is difficult due to the nature of sarcastic tweets, which vary based on the topic, region, the user‘s attitude, culture, terminologies, and other criteria. In addition to these difficulties, detecting sarcasm in Arabic has its challenges due to its complexities, such as being morphologically rich, having many different dialects, and having low resources. In this research, we present our submission of (iSarcasmEval) sub-task A of the shared task on SemEval 2022. In Sub-task A; we determine whether the tweets are sarcastic or non-sarcastic. We implemented different approaches based on Transformers. First, we fine-tuned the AraBERT, MARABERT, and AraELECTRA. One of the challenges that faced us was that the data was not balanced. Non-sarcastic data is much more than sarcastic. We used data augmentation techniques to balance the two classes, significantly affecting the performance. The performance F1 score of the three models was 87%, 90%, and 91%, respectively. Then we boosted the three models by developing an ensemble model based on hard voting. The final performance F1 Score was 93%.</abstract>
<identifier type="citekey">mohamed-kamr-mohamed-2022-akabert</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.124</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.124/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>885</start>
<end>890</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T akaBERT at SemEval-2022 Task 6: An Ensemble Transformer-based Model for Arabic Sarcasm Detection
%A Mohamed Kamr, Abdulrahman
%A Mohamed, Ensaf
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F mohamed-kamr-mohamed-2022-akabert
%X Due to the widespread usage of social media sites and the enormous number of users who utilize irony implicit words in most of their tweets and posts, it has become necessary to detect sarcasm, which strongly influences understanding and analyzing the crowd‘s opinions. Detecting sarcasm is difficult due to the nature of sarcastic tweets, which vary based on the topic, region, the user‘s attitude, culture, terminologies, and other criteria. In addition to these difficulties, detecting sarcasm in Arabic has its challenges due to its complexities, such as being morphologically rich, having many different dialects, and having low resources. In this research, we present our submission of (iSarcasmEval) sub-task A of the shared task on SemEval 2022. In Sub-task A; we determine whether the tweets are sarcastic or non-sarcastic. We implemented different approaches based on Transformers. First, we fine-tuned the AraBERT, MARABERT, and AraELECTRA. One of the challenges that faced us was that the data was not balanced. Non-sarcastic data is much more than sarcastic. We used data augmentation techniques to balance the two classes, significantly affecting the performance. The performance F1 score of the three models was 87%, 90%, and 91%, respectively. Then we boosted the three models by developing an ensemble model based on hard voting. The final performance F1 Score was 93%.
%R 10.18653/v1/2022.semeval-1.124
%U https://aclanthology.org/2022.semeval-1.124/
%U https://doi.org/10.18653/v1/2022.semeval-1.124
%P 885-890
Markdown (Informal)
[akaBERT at SemEval-2022 Task 6: An Ensemble Transformer-based Model for Arabic Sarcasm Detection](https://aclanthology.org/2022.semeval-1.124/) (Mohamed Kamr & Mohamed, SemEval 2022)
ACL