@inproceedings{karan-snajder-2018-cross,
title = "Cross-Domain Detection of Abusive Language Online",
author = "Karan, Mladen and
{\v{S}}najder, Jan",
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/W18-5117",
doi = "10.18653/v1/W18-5117",
pages = "132--137",
abstract = "We investigate to what extent the models trained to detect general abusive language generalize between different datasets labeled with different abusive language types. To this end, we compare the cross-domain performance of simple classification models on nine different datasets, finding that the models fail to generalize to out-domain datasets and that having at least some in-domain data is important. We also show that using the frustratingly simple domain adaptation (Daume III, 2007) in most cases improves the results over in-domain training, especially when used to augment a smaller dataset with a larger one.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karan-snajder-2018-cross">
<titleInfo>
<title>Cross-Domain Detection of Abusive Language Online</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mladen</namePart>
<namePart type="family">Karan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Šnajder</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>We investigate to what extent the models trained to detect general abusive language generalize between different datasets labeled with different abusive language types. To this end, we compare the cross-domain performance of simple classification models on nine different datasets, finding that the models fail to generalize to out-domain datasets and that having at least some in-domain data is important. We also show that using the frustratingly simple domain adaptation (Daume III, 2007) in most cases improves the results over in-domain training, especially when used to augment a smaller dataset with a larger one.</abstract>
<identifier type="citekey">karan-snajder-2018-cross</identifier>
<identifier type="doi">10.18653/v1/W18-5117</identifier>
<location>
<url>https://aclanthology.org/W18-5117</url>
</location>
<part>
<date>2018-10</date>
<extent unit="page">
<start>132</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Domain Detection of Abusive Language Online
%A Karan, Mladen
%A Šnajder, Jan
%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 karan-snajder-2018-cross
%X We investigate to what extent the models trained to detect general abusive language generalize between different datasets labeled with different abusive language types. To this end, we compare the cross-domain performance of simple classification models on nine different datasets, finding that the models fail to generalize to out-domain datasets and that having at least some in-domain data is important. We also show that using the frustratingly simple domain adaptation (Daume III, 2007) in most cases improves the results over in-domain training, especially when used to augment a smaller dataset with a larger one.
%R 10.18653/v1/W18-5117
%U https://aclanthology.org/W18-5117
%U https://doi.org/10.18653/v1/W18-5117
%P 132-137
Markdown (Informal)
[Cross-Domain Detection of Abusive Language Online](https://aclanthology.org/W18-5117) (Karan & Šnajder, ALW 2018)
ACL