@inproceedings{sahlgren-etal-2018-learning,
title = "Learning Representations for Detecting Abusive Language",
author = "Sahlgren, Magnus and
Isbister, Tim and
Olsson, Fredrik",
editor = "Fi{\v{s}}er, Darja and
Huang, Ruihong and
Prabhakaran, Vinodkumar and
Voigt, Rob and
Waseem, Zeerak and
Wernimont, Jacqueline",
booktitle = "Proceedings of the 2nd Workshop on Abusive Language Online ({ALW}2)",
month = oct,
year = "2018",
address = "Brussels, Belgium",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-5115",
doi = "10.18653/v1/W18-5115",
pages = "115--123",
abstract = "This paper discusses the question whether it is possible to learn a generic representation that is useful for detecting various types of abusive language. The approach is inspired by recent advances in transfer learning and word embeddings, and we learn representations from two different datasets containing various degrees of abusive language. We compare the learned representation with two standard approaches; one based on lexica, and one based on data-specific $n$-grams. Our experiments show that learned representations \textit{do} contain useful information that can be used to improve detection performance when training data is limited.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sahlgren-etal-2018-learning">
<titleInfo>
<title>Learning Representations for Detecting Abusive Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Magnus</namePart>
<namePart type="family">Sahlgren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Isbister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fredrik</namePart>
<namePart type="family">Olsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</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">Rob</namePart>
<namePart type="family">Voigt</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>
<name type="personal">
<namePart type="given">Jacqueline</namePart>
<namePart type="family">Wernimont</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Brussels, Belgium</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses the question whether it is possible to learn a generic representation that is useful for detecting various types of abusive language. The approach is inspired by recent advances in transfer learning and word embeddings, and we learn representations from two different datasets containing various degrees of abusive language. We compare the learned representation with two standard approaches; one based on lexica, and one based on data-specific n-grams. Our experiments show that learned representations do contain useful information that can be used to improve detection performance when training data is limited.</abstract>
<identifier type="citekey">sahlgren-etal-2018-learning</identifier>
<identifier type="doi">10.18653/v1/W18-5115</identifier>
<location>
<url>https://aclanthology.org/W18-5115</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>115</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learning Representations for Detecting Abusive Language
%A Sahlgren, Magnus
%A Isbister, Tim
%A Olsson, Fredrik
%Y Fišer, Darja
%Y Huang, Ruihong
%Y Prabhakaran, Vinodkumar
%Y Voigt, Rob
%Y Waseem, Zeerak
%Y Wernimont, Jacqueline
%S Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)
%D 2018
%8 October
%I Association for Computational Linguistics
%C Brussels, Belgium
%F sahlgren-etal-2018-learning
%X This paper discusses the question whether it is possible to learn a generic representation that is useful for detecting various types of abusive language. The approach is inspired by recent advances in transfer learning and word embeddings, and we learn representations from two different datasets containing various degrees of abusive language. We compare the learned representation with two standard approaches; one based on lexica, and one based on data-specific n-grams. Our experiments show that learned representations do contain useful information that can be used to improve detection performance when training data is limited.
%R 10.18653/v1/W18-5115
%U https://aclanthology.org/W18-5115
%U https://doi.org/10.18653/v1/W18-5115
%P 115-123
Markdown (Informal)
[Learning Representations for Detecting Abusive Language](https://aclanthology.org/W18-5115) (Sahlgren et al., ALW 2018)
ACL