@inproceedings{zhang-wang-2023-hhs,
title = "{HHS} at {S}em{E}val-2023 Task 10: A Comparative Analysis of Sexism Detection Based on the {R}o{BERT}a Model",
author = "Zhang, Yao and
Wang, Liqing",
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-1.133",
doi = "10.18653/v1/2023.semeval-1.133",
pages = "963--968",
abstract = "This paper describes the methods and models applied by our team HHS in SubTask-A of SemEval-2023 Task 10 about sexism detection. In this task, we trained with the officially released data and analyzed the performance of five models, TextCNN, BERT, RoBERTa, XLNet, and Sup-SimCSE-RoBERTa. The experiments show that most of the models can achieve good results. Then, we tried data augmentation, model ensemble, dropout, and other operations on several of these models, and compared the results for analysis. In the end, the most effective approach that yielded the best results on the test set involved the following steps: enhancing the sexist data using dropout, feeding it as input to the Sup-SimCSE-RoBERTa model, and providing the raw data as input to the XLNet model. Then, combining the outputs of the two methods led to even better results. This method yielded a Macro-F1 score of 0.823 in the final evaluation phase of the SubTask-A of the competition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-wang-2023-hhs">
<titleInfo>
<title>HHS at SemEval-2023 Task 10: A Comparative Analysis of Sexism Detection Based on the RoBERTa Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqing</namePart>
<namePart type="family">Wang</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 the methods and models applied by our team HHS in SubTask-A of SemEval-2023 Task 10 about sexism detection. In this task, we trained with the officially released data and analyzed the performance of five models, TextCNN, BERT, RoBERTa, XLNet, and Sup-SimCSE-RoBERTa. The experiments show that most of the models can achieve good results. Then, we tried data augmentation, model ensemble, dropout, and other operations on several of these models, and compared the results for analysis. In the end, the most effective approach that yielded the best results on the test set involved the following steps: enhancing the sexist data using dropout, feeding it as input to the Sup-SimCSE-RoBERTa model, and providing the raw data as input to the XLNet model. Then, combining the outputs of the two methods led to even better results. This method yielded a Macro-F1 score of 0.823 in the final evaluation phase of the SubTask-A of the competition.</abstract>
<identifier type="citekey">zhang-wang-2023-hhs</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.133</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.133</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>963</start>
<end>968</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HHS at SemEval-2023 Task 10: A Comparative Analysis of Sexism Detection Based on the RoBERTa Model
%A Zhang, Yao
%A Wang, Liqing
%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 zhang-wang-2023-hhs
%X This paper describes the methods and models applied by our team HHS in SubTask-A of SemEval-2023 Task 10 about sexism detection. In this task, we trained with the officially released data and analyzed the performance of five models, TextCNN, BERT, RoBERTa, XLNet, and Sup-SimCSE-RoBERTa. The experiments show that most of the models can achieve good results. Then, we tried data augmentation, model ensemble, dropout, and other operations on several of these models, and compared the results for analysis. In the end, the most effective approach that yielded the best results on the test set involved the following steps: enhancing the sexist data using dropout, feeding it as input to the Sup-SimCSE-RoBERTa model, and providing the raw data as input to the XLNet model. Then, combining the outputs of the two methods led to even better results. This method yielded a Macro-F1 score of 0.823 in the final evaluation phase of the SubTask-A of the competition.
%R 10.18653/v1/2023.semeval-1.133
%U https://aclanthology.org/2023.semeval-1.133
%U https://doi.org/10.18653/v1/2023.semeval-1.133
%P 963-968
Markdown (Informal)
[HHS at SemEval-2023 Task 10: A Comparative Analysis of Sexism Detection Based on the RoBERTa Model](https://aclanthology.org/2023.semeval-1.133) (Zhang & Wang, SemEval 2023)
ACL