@inproceedings{segura-bedmar-2023-hulat-semeval,
title = "{HULAT} at {S}em{E}val-2023 Task 10: Data Augmentation for Pre-trained Transformers Applied to the Detection of Sexism in Social Media",
author = "Segura-Bedmar, Isabel",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.26",
doi = "10.18653/v1/2023.semeval-1.26",
pages = "184--192",
abstract = "This paper describes our participation in SemEval-2023 Task 10, whose goal is the detection of sexism in social media. We explore some of the most popular transformer models such as BERT, DistilBERT, RoBERTa, and XLNet. We also study different data augmentation techniques to increase the training dataset. During the development phase, our best results were obtained by using RoBERTa and data augmentation for tasks B and C. However, the use of synthetic data does not improve the results for task C. We participated in the three subtasks. Our approach still has much room for improvement, especially in the two fine-grained classifications. All our code is available in the repository \url{https://github.com/isegura/hulat_edos}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="segura-bedmar-2023-hulat-semeval">
<titleInfo>
<title>HULAT at SemEval-2023 Task 10: Data Augmentation for Pre-trained Transformers Applied to the Detection of Sexism in Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isabel</namePart>
<namePart type="family">Segura-Bedmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our participation in SemEval-2023 Task 10, whose goal is the detection of sexism in social media. We explore some of the most popular transformer models such as BERT, DistilBERT, RoBERTa, and XLNet. We also study different data augmentation techniques to increase the training dataset. During the development phase, our best results were obtained by using RoBERTa and data augmentation for tasks B and C. However, the use of synthetic data does not improve the results for task C. We participated in the three subtasks. Our approach still has much room for improvement, especially in the two fine-grained classifications. All our code is available in the repository https://github.com/isegura/hulat_edos.</abstract>
<identifier type="citekey">segura-bedmar-2023-hulat-semeval</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.26</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.26</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>184</start>
<end>192</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HULAT at SemEval-2023 Task 10: Data Augmentation for Pre-trained Transformers Applied to the Detection of Sexism in Social Media
%A Segura-Bedmar, Isabel
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F segura-bedmar-2023-hulat-semeval
%X This paper describes our participation in SemEval-2023 Task 10, whose goal is the detection of sexism in social media. We explore some of the most popular transformer models such as BERT, DistilBERT, RoBERTa, and XLNet. We also study different data augmentation techniques to increase the training dataset. During the development phase, our best results were obtained by using RoBERTa and data augmentation for tasks B and C. However, the use of synthetic data does not improve the results for task C. We participated in the three subtasks. Our approach still has much room for improvement, especially in the two fine-grained classifications. All our code is available in the repository https://github.com/isegura/hulat_edos.
%R 10.18653/v1/2023.semeval-1.26
%U https://aclanthology.org/2023.semeval-1.26
%U https://doi.org/10.18653/v1/2023.semeval-1.26
%P 184-192
Markdown (Informal)
[HULAT at SemEval-2023 Task 10: Data Augmentation for Pre-trained Transformers Applied to the Detection of Sexism in Social Media](https://aclanthology.org/2023.semeval-1.26) (Segura-Bedmar, SemEval 2023)
ACL