@inproceedings{koufakou-etal-2020-hurtbert,
title = "{H}urt{BERT}: Incorporating Lexical Features with {BERT} for the Detection of Abusive Language",
author = "Koufakou, Anna and
Pamungkas, Endang Wahyu and
Basile, Valerio and
Patti, Viviana",
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-1.5",
doi = "10.18653/v1/2020.alw-1.5",
pages = "34--43",
abstract = "The detection of abusive or offensive remarks in social texts has received significant attention in research. In several related shared tasks, BERT has been shown to be the state-of-the-art. In this paper, we propose to utilize lexical features derived from a hate lexicon towards improving the performance of BERT in such tasks. We explore different ways to utilize the lexical features in the form of lexicon-based encodings at the sentence level or embeddings at the word level. We provide an extensive dataset evaluation that addresses in-domain as well as cross-domain detection of abusive content to render a complete picture. Our results indicate that our proposed models combining BERT with lexical features help improve over a baseline BERT model in many of our in-domain and cross-domain experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koufakou-etal-2020-hurtbert">
<titleInfo>
<title>HurtBERT: Incorporating Lexical Features with BERT for the Detection of Abusive Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Koufakou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Endang</namePart>
<namePart type="given">Wahyu</namePart>
<namePart type="family">Pamungkas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviana</namePart>
<namePart type="family">Patti</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>The detection of abusive or offensive remarks in social texts has received significant attention in research. In several related shared tasks, BERT has been shown to be the state-of-the-art. In this paper, we propose to utilize lexical features derived from a hate lexicon towards improving the performance of BERT in such tasks. We explore different ways to utilize the lexical features in the form of lexicon-based encodings at the sentence level or embeddings at the word level. We provide an extensive dataset evaluation that addresses in-domain as well as cross-domain detection of abusive content to render a complete picture. Our results indicate that our proposed models combining BERT with lexical features help improve over a baseline BERT model in many of our in-domain and cross-domain experiments.</abstract>
<identifier type="citekey">koufakou-etal-2020-hurtbert</identifier>
<identifier type="doi">10.18653/v1/2020.alw-1.5</identifier>
<location>
<url>https://aclanthology.org/2020.alw-1.5</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>34</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HurtBERT: Incorporating Lexical Features with BERT for the Detection of Abusive Language
%A Koufakou, Anna
%A Pamungkas, Endang Wahyu
%A Basile, Valerio
%A Patti, Viviana
%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 koufakou-etal-2020-hurtbert
%X The detection of abusive or offensive remarks in social texts has received significant attention in research. In several related shared tasks, BERT has been shown to be the state-of-the-art. In this paper, we propose to utilize lexical features derived from a hate lexicon towards improving the performance of BERT in such tasks. We explore different ways to utilize the lexical features in the form of lexicon-based encodings at the sentence level or embeddings at the word level. We provide an extensive dataset evaluation that addresses in-domain as well as cross-domain detection of abusive content to render a complete picture. Our results indicate that our proposed models combining BERT with lexical features help improve over a baseline BERT model in many of our in-domain and cross-domain experiments.
%R 10.18653/v1/2020.alw-1.5
%U https://aclanthology.org/2020.alw-1.5
%U https://doi.org/10.18653/v1/2020.alw-1.5
%P 34-43
Markdown (Informal)
[HurtBERT: Incorporating Lexical Features with BERT for the Detection of Abusive Language](https://aclanthology.org/2020.alw-1.5) (Koufakou et al., ALW 2020)
ACL