@inproceedings{hahn-etal-2021-modeling,
title = "Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces",
author = "Hahn, Vanessa and
Ruiter, Dana and
Kleinbauer, Thomas and
Klakow, Dietrich",
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-1.2",
doi = "10.18653/v1/2021.woah-1.2",
pages = "6--16",
abstract = "Hate speech and profanity detection suffer from data sparsity, especially for languages other than English, due to the subjective nature of the tasks and the resulting annotation incompatibility of existing corpora. In this study, we identify profane subspaces in word and sentence representations and explore their generalization capability on a variety of similar and distant target tasks in a zero-shot setting. This is done monolingually (German) and cross-lingually to closely-related (English), distantly-related (French) and non-related (Arabic) tasks. We observe that, on both similar and distant target tasks and across all languages, the subspace-based representations transfer more effectively than standard BERT representations in the zero-shot setting, with improvements between F1 +10.9 and F1 +42.9 over the baselines across all tested monolingual and cross-lingual scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hahn-etal-2021-modeling">
<titleInfo>
<title>Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vanessa</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Ruiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Kleinbauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dietrich</namePart>
<namePart type="family">Klakow</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>Hate speech and profanity detection suffer from data sparsity, especially for languages other than English, due to the subjective nature of the tasks and the resulting annotation incompatibility of existing corpora. In this study, we identify profane subspaces in word and sentence representations and explore their generalization capability on a variety of similar and distant target tasks in a zero-shot setting. This is done monolingually (German) and cross-lingually to closely-related (English), distantly-related (French) and non-related (Arabic) tasks. We observe that, on both similar and distant target tasks and across all languages, the subspace-based representations transfer more effectively than standard BERT representations in the zero-shot setting, with improvements between F1 +10.9 and F1 +42.9 over the baselines across all tested monolingual and cross-lingual scenarios.</abstract>
<identifier type="citekey">hahn-etal-2021-modeling</identifier>
<identifier type="doi">10.18653/v1/2021.woah-1.2</identifier>
<location>
<url>https://aclanthology.org/2021.woah-1.2</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>6</start>
<end>16</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces
%A Hahn, Vanessa
%A Ruiter, Dana
%A Kleinbauer, Thomas
%A Klakow, Dietrich
%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 hahn-etal-2021-modeling
%X Hate speech and profanity detection suffer from data sparsity, especially for languages other than English, due to the subjective nature of the tasks and the resulting annotation incompatibility of existing corpora. In this study, we identify profane subspaces in word and sentence representations and explore their generalization capability on a variety of similar and distant target tasks in a zero-shot setting. This is done monolingually (German) and cross-lingually to closely-related (English), distantly-related (French) and non-related (Arabic) tasks. We observe that, on both similar and distant target tasks and across all languages, the subspace-based representations transfer more effectively than standard BERT representations in the zero-shot setting, with improvements between F1 +10.9 and F1 +42.9 over the baselines across all tested monolingual and cross-lingual scenarios.
%R 10.18653/v1/2021.woah-1.2
%U https://aclanthology.org/2021.woah-1.2
%U https://doi.org/10.18653/v1/2021.woah-1.2
%P 6-16
Markdown (Informal)
[Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces](https://aclanthology.org/2021.woah-1.2) (Hahn et al., WOAH 2021)
ACL