@inproceedings{qarqaz-etal-2021-r00,
title = "R00 at {NLP}4{IF}-2021 Fighting {COVID}-19 Infodemic with Transformers and More Transformers",
author = "Qarqaz, Ahmed and
Abujaber, Dia and
Abdullah, Malak",
editor = "Feldman, Anna and
Da San Martino, Giovanni and
Leberknight, Chris and
Nakov, Preslav",
booktitle = "Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4if-1.15",
doi = "10.18653/v1/2021.nlp4if-1.15",
pages = "104--109",
abstract = "This paper describes the winning model in the Arabic NLP4IF shared task for fighting the COVID-19 infodemic. The goal of the shared task is to check disinformation about COVID-19 in Arabic tweets. Our proposed model has been ranked 1st with an F1-Score of 0.780 and an Accuracy score of 0.762. A variety of transformer-based pre-trained language models have been experimented with through this study. The best-scored model is an ensemble of AraBERT-Base, Asafya-BERT, and ARBERT models. One of the study{'}s key findings is showing the effect the pre-processing can have on every model{'}s score. In addition to describing the winning model, the current study shows the error analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qarqaz-etal-2021-r00">
<titleInfo>
<title>R00 at NLP4IF-2021 Fighting COVID-19 Infodemic with Transformers and More Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Qarqaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dia</namePart>
<namePart type="family">Abujaber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malak</namePart>
<namePart type="family">Abdullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Leberknight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the winning model in the Arabic NLP4IF shared task for fighting the COVID-19 infodemic. The goal of the shared task is to check disinformation about COVID-19 in Arabic tweets. Our proposed model has been ranked 1st with an F1-Score of 0.780 and an Accuracy score of 0.762. A variety of transformer-based pre-trained language models have been experimented with through this study. The best-scored model is an ensemble of AraBERT-Base, Asafya-BERT, and ARBERT models. One of the study’s key findings is showing the effect the pre-processing can have on every model’s score. In addition to describing the winning model, the current study shows the error analysis.</abstract>
<identifier type="citekey">qarqaz-etal-2021-r00</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4if-1.15</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4if-1.15</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>104</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T R00 at NLP4IF-2021 Fighting COVID-19 Infodemic with Transformers and More Transformers
%A Qarqaz, Ahmed
%A Abujaber, Dia
%A Abdullah, Malak
%Y Feldman, Anna
%Y Da San Martino, Giovanni
%Y Leberknight, Chris
%Y Nakov, Preslav
%S Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F qarqaz-etal-2021-r00
%X This paper describes the winning model in the Arabic NLP4IF shared task for fighting the COVID-19 infodemic. The goal of the shared task is to check disinformation about COVID-19 in Arabic tweets. Our proposed model has been ranked 1st with an F1-Score of 0.780 and an Accuracy score of 0.762. A variety of transformer-based pre-trained language models have been experimented with through this study. The best-scored model is an ensemble of AraBERT-Base, Asafya-BERT, and ARBERT models. One of the study’s key findings is showing the effect the pre-processing can have on every model’s score. In addition to describing the winning model, the current study shows the error analysis.
%R 10.18653/v1/2021.nlp4if-1.15
%U https://aclanthology.org/2021.nlp4if-1.15
%U https://doi.org/10.18653/v1/2021.nlp4if-1.15
%P 104-109
Markdown (Informal)
[R00 at NLP4IF-2021 Fighting COVID-19 Infodemic with Transformers and More Transformers](https://aclanthology.org/2021.nlp4if-1.15) (Qarqaz et al., NLP4IF 2021)
ACL