@inproceedings{singh-li-2021-exploiting,
title = "Exploiting Auxiliary Data for Offensive Language Detection with Bidirectional Transformers",
author = "Singh, Sumer and
Li, Sheng",
editor = "Mostafazadeh Davani, Aida and
Kiela, Douwe and
Lambert, Mathias and
Vidgen, Bertie and
Prabhakaran, Vinodkumar and
Waseem, Zeerak",
booktitle = "Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.woah-1.1",
doi = "10.18653/v1/2021.woah-1.1",
pages = "1--5",
abstract = "Offensive language detection (OLD) has received increasing attention due to its societal impact. Recent work shows that bidirectional transformer based methods obtain impressive performance on OLD. However, such methods usually rely on large-scale well-labeled OLD datasets for model training. To address the issue of data/label scarcity in OLD, in this paper, we propose a simple yet effective domain adaptation approach to train bidirectional transformers. Our approach introduces domain adaptation (DA) training procedures to ALBERT, such that it can effectively exploit auxiliary data from source domains to improve the OLD performance in a target domain. Experimental results on benchmark datasets show that our approach, ALBERT (DA), obtains the state-of-the-art performance in most cases. Particularly, our approach significantly benefits underrepresented and under-performing classes, with a significant improvement over ALBERT.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-li-2021-exploiting">
<titleInfo>
<title>Exploiting Auxiliary Data for Offensive Language Detection with Bidirectional Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sumer</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aida</namePart>
<namePart type="family">Mostafazadeh Davani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douwe</namePart>
<namePart type="family">Kiela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathias</namePart>
<namePart type="family">Lambert</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>Offensive language detection (OLD) has received increasing attention due to its societal impact. Recent work shows that bidirectional transformer based methods obtain impressive performance on OLD. However, such methods usually rely on large-scale well-labeled OLD datasets for model training. To address the issue of data/label scarcity in OLD, in this paper, we propose a simple yet effective domain adaptation approach to train bidirectional transformers. Our approach introduces domain adaptation (DA) training procedures to ALBERT, such that it can effectively exploit auxiliary data from source domains to improve the OLD performance in a target domain. Experimental results on benchmark datasets show that our approach, ALBERT (DA), obtains the state-of-the-art performance in most cases. Particularly, our approach significantly benefits underrepresented and under-performing classes, with a significant improvement over ALBERT.</abstract>
<identifier type="citekey">singh-li-2021-exploiting</identifier>
<identifier type="doi">10.18653/v1/2021.woah-1.1</identifier>
<location>
<url>https://aclanthology.org/2021.woah-1.1</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1</start>
<end>5</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Auxiliary Data for Offensive Language Detection with Bidirectional Transformers
%A Singh, Sumer
%A Li, Sheng
%Y Mostafazadeh Davani, Aida
%Y Kiela, Douwe
%Y Lambert, Mathias
%Y Vidgen, Bertie
%Y Prabhakaran, Vinodkumar
%Y Waseem, Zeerak
%S Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F singh-li-2021-exploiting
%X Offensive language detection (OLD) has received increasing attention due to its societal impact. Recent work shows that bidirectional transformer based methods obtain impressive performance on OLD. However, such methods usually rely on large-scale well-labeled OLD datasets for model training. To address the issue of data/label scarcity in OLD, in this paper, we propose a simple yet effective domain adaptation approach to train bidirectional transformers. Our approach introduces domain adaptation (DA) training procedures to ALBERT, such that it can effectively exploit auxiliary data from source domains to improve the OLD performance in a target domain. Experimental results on benchmark datasets show that our approach, ALBERT (DA), obtains the state-of-the-art performance in most cases. Particularly, our approach significantly benefits underrepresented and under-performing classes, with a significant improvement over ALBERT.
%R 10.18653/v1/2021.woah-1.1
%U https://aclanthology.org/2021.woah-1.1
%U https://doi.org/10.18653/v1/2021.woah-1.1
%P 1-5
Markdown (Informal)
[Exploiting Auxiliary Data for Offensive Language Detection with Bidirectional Transformers](https://aclanthology.org/2021.woah-1.1) (Singh & Li, WOAH 2021)
ACL