@inproceedings{isaksen-gamback-2020-using,
title = "Using Transfer-based Language Models to Detect Hateful and Offensive Language Online",
author = {Isaksen, Vebj{\o}rn and
Gamb{\"a}ck, Bj{\"o}rn},
editor = "Akiwowo, Seyi and
Vidgen, Bertie and
Prabhakaran, Vinodkumar and
Waseem, Zeerak",
booktitle = "Proceedings of the Fourth Workshop on Online Abuse and Harms",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.alw-1.3",
doi = "10.18653/v1/2020.alw-1.3",
pages = "16--27",
abstract = "Distinguishing hate speech from non-hate offensive language is challenging, as hate speech not always includes offensive slurs and offensive language not always express hate. Here, four deep learners based on the Bidirectional Encoder Representations from Transformers (BERT), with either general or domain-specific language models, were tested against two datasets containing tweets labelled as either {`}Hateful{'}, {`}Normal{'} or {`}Offensive{'}. The results indicate that the attention-based models profoundly confuse hate speech with offensive and normal language. However, the pre-trained models outperform state-of-the-art results in terms of accurately predicting the hateful instances.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="isaksen-gamback-2020-using">
<titleInfo>
<title>Using Transfer-based Language Models to Detect Hateful and Offensive Language Online</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vebjørn</namePart>
<namePart type="family">Isaksen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Björn</namePart>
<namePart type="family">Gambäck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Online Abuse and Harms</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seyi</namePart>
<namePart type="family">Akiwowo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bertie</namePart>
<namePart type="family">Vidgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinodkumar</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeerak</namePart>
<namePart type="family">Waseem</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>Distinguishing hate speech from non-hate offensive language is challenging, as hate speech not always includes offensive slurs and offensive language not always express hate. Here, four deep learners based on the Bidirectional Encoder Representations from Transformers (BERT), with either general or domain-specific language models, were tested against two datasets containing tweets labelled as either ‘Hateful’, ‘Normal’ or ‘Offensive’. The results indicate that the attention-based models profoundly confuse hate speech with offensive and normal language. However, the pre-trained models outperform state-of-the-art results in terms of accurately predicting the hateful instances.</abstract>
<identifier type="citekey">isaksen-gamback-2020-using</identifier>
<identifier type="doi">10.18653/v1/2020.alw-1.3</identifier>
<location>
<url>https://aclanthology.org/2020.alw-1.3</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>16</start>
<end>27</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Transfer-based Language Models to Detect Hateful and Offensive Language Online
%A Isaksen, Vebjørn
%A Gambäck, Björn
%Y Akiwowo, Seyi
%Y Vidgen, Bertie
%Y Prabhakaran, Vinodkumar
%Y Waseem, Zeerak
%S Proceedings of the Fourth Workshop on Online Abuse and Harms
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F isaksen-gamback-2020-using
%X Distinguishing hate speech from non-hate offensive language is challenging, as hate speech not always includes offensive slurs and offensive language not always express hate. Here, four deep learners based on the Bidirectional Encoder Representations from Transformers (BERT), with either general or domain-specific language models, were tested against two datasets containing tweets labelled as either ‘Hateful’, ‘Normal’ or ‘Offensive’. The results indicate that the attention-based models profoundly confuse hate speech with offensive and normal language. However, the pre-trained models outperform state-of-the-art results in terms of accurately predicting the hateful instances.
%R 10.18653/v1/2020.alw-1.3
%U https://aclanthology.org/2020.alw-1.3
%U https://doi.org/10.18653/v1/2020.alw-1.3
%P 16-27
Markdown (Informal)
[Using Transfer-based Language Models to Detect Hateful and Offensive Language Online](https://aclanthology.org/2020.alw-1.3) (Isaksen & Gambäck, ALW 2020)
ACL