@inproceedings{coria-etal-2020-metric,
title = "A Metric Learning Approach to Misogyny Categorization",
author = "Coria, Juan Manuel and
Ghannay, Sahar and
Rosset, Sophie and
Bredin, Herv{\'e}",
editor = "Gella, Spandana and
Welbl, Johannes and
Rei, Marek and
Petroni, Fabio and
Lewis, Patrick and
Strubell, Emma and
Seo, Minjoon and
Hajishirzi, Hannaneh",
booktitle = "Proceedings of the 5th Workshop on Representation Learning for NLP",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.repl4nlp-1.12/",
doi = "10.18653/v1/2020.repl4nlp-1.12",
pages = "89--94",
abstract = "The task of automatic misogyny identification and categorization has not received as much attention as other natural language tasks have, even though it is crucial for identifying hate speech in social Internet interactions. In this work, we address this sentence classification task from a representation learning perspective, using both a bidirectional LSTM and BERT optimized with the following metric learning loss functions: contrastive loss, triplet loss, center loss, congenerous cosine loss and additive angular margin loss. We set new state-of-the-art for the task with our fine-tuned BERT, whose sentence embeddings can be compared with a simple cosine distance, and we release all our code as open source for easy reproducibility. Moreover, we find that almost every loss function performs equally well in this setting, matching the regular cross entropy loss."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="coria-etal-2020-metric">
<titleInfo>
<title>A Metric Learning Approach to Misogyny Categorization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Coria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahar</namePart>
<namePart type="family">Ghannay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Rosset</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hervé</namePart>
<namePart type="family">Bredin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Workshop on Representation Learning for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Welbl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marek</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Petroni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emma</namePart>
<namePart type="family">Strubell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjoon</namePart>
<namePart type="family">Seo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</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 task of automatic misogyny identification and categorization has not received as much attention as other natural language tasks have, even though it is crucial for identifying hate speech in social Internet interactions. In this work, we address this sentence classification task from a representation learning perspective, using both a bidirectional LSTM and BERT optimized with the following metric learning loss functions: contrastive loss, triplet loss, center loss, congenerous cosine loss and additive angular margin loss. We set new state-of-the-art for the task with our fine-tuned BERT, whose sentence embeddings can be compared with a simple cosine distance, and we release all our code as open source for easy reproducibility. Moreover, we find that almost every loss function performs equally well in this setting, matching the regular cross entropy loss.</abstract>
<identifier type="citekey">coria-etal-2020-metric</identifier>
<identifier type="doi">10.18653/v1/2020.repl4nlp-1.12</identifier>
<location>
<url>https://aclanthology.org/2020.repl4nlp-1.12/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>89</start>
<end>94</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Metric Learning Approach to Misogyny Categorization
%A Coria, Juan Manuel
%A Ghannay, Sahar
%A Rosset, Sophie
%A Bredin, Hervé
%Y Gella, Spandana
%Y Welbl, Johannes
%Y Rei, Marek
%Y Petroni, Fabio
%Y Lewis, Patrick
%Y Strubell, Emma
%Y Seo, Minjoon
%Y Hajishirzi, Hannaneh
%S Proceedings of the 5th Workshop on Representation Learning for NLP
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F coria-etal-2020-metric
%X The task of automatic misogyny identification and categorization has not received as much attention as other natural language tasks have, even though it is crucial for identifying hate speech in social Internet interactions. In this work, we address this sentence classification task from a representation learning perspective, using both a bidirectional LSTM and BERT optimized with the following metric learning loss functions: contrastive loss, triplet loss, center loss, congenerous cosine loss and additive angular margin loss. We set new state-of-the-art for the task with our fine-tuned BERT, whose sentence embeddings can be compared with a simple cosine distance, and we release all our code as open source for easy reproducibility. Moreover, we find that almost every loss function performs equally well in this setting, matching the regular cross entropy loss.
%R 10.18653/v1/2020.repl4nlp-1.12
%U https://aclanthology.org/2020.repl4nlp-1.12/
%U https://doi.org/10.18653/v1/2020.repl4nlp-1.12
%P 89-94
Markdown (Informal)
[A Metric Learning Approach to Misogyny Categorization](https://aclanthology.org/2020.repl4nlp-1.12/) (Coria et al., RepL4NLP 2020)
ACL