@inproceedings{djandji-etal-2020-multi,
title = "Multi-Task Learning using {A}ra{B}ert for Offensive Language Detection",
author = "Djandji, Marc and
Baly, Fady and
Antoun, Wissam and
Hajj, Hazem",
editor = "Al-Khalifa, Hend and
Magdy, Walid and
Darwish, Kareem and
Elsayed, Tamer and
Mubarak, Hamdy",
booktitle = "Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resource Association",
url = "https://aclanthology.org/2020.osact-1.16",
pages = "97--101",
abstract = "The use of social media platforms has become more prevalent, which has provided tremendous opportunities for people to connect but has also opened the door for misuse with the spread of hate speech and offensive language. This phenomenon has been driving more and more people to more extreme reactions and online aggression, sometimes causing physical harm to individuals or groups of people. There is a need to control and prevent such misuse of online social media through automatic detection of profane language. The shared task on Offensive Language Detection at the OSACT4 has aimed at achieving state of art profane language detection methods for Arabic social media. Our team {``}BERTologists{''} tackled this problem by leveraging state of the art pretrained Arabic language model, AraBERT, that we augment with the addition of Multi-task learning to enable our model to learn efficiently from little data. Our Multitask AraBERT approach achieved the second place in both subtasks A {\&} B, which shows that the model performs consistently across different tasks.",
language = "English",
ISBN = "979-10-95546-51-1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="djandji-etal-2020-multi">
<titleInfo>
<title>Multi-Task Learning using AraBert for Offensive Language Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marc</namePart>
<namePart type="family">Djandji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fady</namePart>
<namePart type="family">Baly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wissam</namePart>
<namePart type="family">Antoun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hazem</namePart>
<namePart type="family">Hajj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection</title>
</titleInfo>
<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">Walid</namePart>
<namePart type="family">Magdy</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">Tamer</namePart>
<namePart type="family">Elsayed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resource Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-51-1</identifier>
</relatedItem>
<abstract>The use of social media platforms has become more prevalent, which has provided tremendous opportunities for people to connect but has also opened the door for misuse with the spread of hate speech and offensive language. This phenomenon has been driving more and more people to more extreme reactions and online aggression, sometimes causing physical harm to individuals or groups of people. There is a need to control and prevent such misuse of online social media through automatic detection of profane language. The shared task on Offensive Language Detection at the OSACT4 has aimed at achieving state of art profane language detection methods for Arabic social media. Our team “BERTologists” tackled this problem by leveraging state of the art pretrained Arabic language model, AraBERT, that we augment with the addition of Multi-task learning to enable our model to learn efficiently from little data. Our Multitask AraBERT approach achieved the second place in both subtasks A & B, which shows that the model performs consistently across different tasks.</abstract>
<identifier type="citekey">djandji-etal-2020-multi</identifier>
<location>
<url>https://aclanthology.org/2020.osact-1.16</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>97</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Task Learning using AraBert for Offensive Language Detection
%A Djandji, Marc
%A Baly, Fady
%A Antoun, Wissam
%A Hajj, Hazem
%Y Al-Khalifa, Hend
%Y Magdy, Walid
%Y Darwish, Kareem
%Y Elsayed, Tamer
%Y Mubarak, Hamdy
%S Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection
%D 2020
%8 May
%I European Language Resource Association
%C Marseille, France
%@ 979-10-95546-51-1
%G English
%F djandji-etal-2020-multi
%X The use of social media platforms has become more prevalent, which has provided tremendous opportunities for people to connect but has also opened the door for misuse with the spread of hate speech and offensive language. This phenomenon has been driving more and more people to more extreme reactions and online aggression, sometimes causing physical harm to individuals or groups of people. There is a need to control and prevent such misuse of online social media through automatic detection of profane language. The shared task on Offensive Language Detection at the OSACT4 has aimed at achieving state of art profane language detection methods for Arabic social media. Our team “BERTologists” tackled this problem by leveraging state of the art pretrained Arabic language model, AraBERT, that we augment with the addition of Multi-task learning to enable our model to learn efficiently from little data. Our Multitask AraBERT approach achieved the second place in both subtasks A & B, which shows that the model performs consistently across different tasks.
%U https://aclanthology.org/2020.osact-1.16
%P 97-101
Markdown (Informal)
[Multi-Task Learning using AraBert for Offensive Language Detection](https://aclanthology.org/2020.osact-1.16) (Djandji et al., OSACT 2020)
ACL
- Marc Djandji, Fady Baly, Wissam Antoun, and Hazem Hajj. 2020. Multi-Task Learning using AraBert for Offensive Language Detection. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 97–101, Marseille, France. European Language Resource Association.