@inproceedings{hussein-etal-2021-damascusteam,
title = "{D}amascus{T}eam at {NLP}4{IF}2021: Fighting the {A}rabic {COVID}-19 Infodemic on {T}witter Using {A}ra{BERT}",
author = "Hussein, Ahmad and
Ghneim, Nada and
Joukhadar, Ammar",
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-1.13",
doi = "10.18653/v1/2021.nlp4if-1.13",
pages = "93--98",
abstract = "The objective of this work was the introduction of an effective approach based on the AraBERT language model for fighting Tweets COVID-19 Infodemic. It was arranged in the form of a two-step pipeline, where the first step involved a series of pre-processing procedures to transform Twitter jargon, including emojis and emoticons, into plain text, and the second step exploited a version of AraBERT, which was pre-trained on plain text, to fine-tune and classify the tweets with respect to their Label. The use of language models pre-trained on plain texts rather than on tweets was motivated by the necessity to address two critical issues shown by the scientific literature, namely (1) pre-trained language models are widely available in many languages, avoiding the time-consuming and resource-intensive model training directly on tweets from scratch, allowing to focus only on their fine-tuning; (2) available plain text corpora are larger than tweet-only ones, allowing for better performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hussein-etal-2021-damascusteam">
<titleInfo>
<title>DamascusTeam at NLP4IF2021: Fighting the Arabic COVID-19 Infodemic on Twitter Using AraBERT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmad</namePart>
<namePart type="family">Hussein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nada</namePart>
<namePart type="family">Ghneim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ammar</namePart>
<namePart type="family">Joukhadar</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>The objective of this work was the introduction of an effective approach based on the AraBERT language model for fighting Tweets COVID-19 Infodemic. It was arranged in the form of a two-step pipeline, where the first step involved a series of pre-processing procedures to transform Twitter jargon, including emojis and emoticons, into plain text, and the second step exploited a version of AraBERT, which was pre-trained on plain text, to fine-tune and classify the tweets with respect to their Label. The use of language models pre-trained on plain texts rather than on tweets was motivated by the necessity to address two critical issues shown by the scientific literature, namely (1) pre-trained language models are widely available in many languages, avoiding the time-consuming and resource-intensive model training directly on tweets from scratch, allowing to focus only on their fine-tuning; (2) available plain text corpora are larger than tweet-only ones, allowing for better performance.</abstract>
<identifier type="citekey">hussein-etal-2021-damascusteam</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4if-1.13</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4if-1.13</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>93</start>
<end>98</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DamascusTeam at NLP4IF2021: Fighting the Arabic COVID-19 Infodemic on Twitter Using AraBERT
%A Hussein, Ahmad
%A Ghneim, Nada
%A Joukhadar, Ammar
%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 hussein-etal-2021-damascusteam
%X The objective of this work was the introduction of an effective approach based on the AraBERT language model for fighting Tweets COVID-19 Infodemic. It was arranged in the form of a two-step pipeline, where the first step involved a series of pre-processing procedures to transform Twitter jargon, including emojis and emoticons, into plain text, and the second step exploited a version of AraBERT, which was pre-trained on plain text, to fine-tune and classify the tweets with respect to their Label. The use of language models pre-trained on plain texts rather than on tweets was motivated by the necessity to address two critical issues shown by the scientific literature, namely (1) pre-trained language models are widely available in many languages, avoiding the time-consuming and resource-intensive model training directly on tweets from scratch, allowing to focus only on their fine-tuning; (2) available plain text corpora are larger than tweet-only ones, allowing for better performance.
%R 10.18653/v1/2021.nlp4if-1.13
%U https://aclanthology.org/2021.nlp4if-1.13
%U https://doi.org/10.18653/v1/2021.nlp4if-1.13
%P 93-98
Markdown (Informal)
[DamascusTeam at NLP4IF2021: Fighting the Arabic COVID-19 Infodemic on Twitter Using AraBERT](https://aclanthology.org/2021.nlp4if-1.13) (Hussein et al., NLP4IF 2021)
ACL