@inproceedings{feely-etal-2023-qcon,
title = "{QC}on at {S}em{E}val-2023 Task 10: Data Augmentation and Model Ensembling for Detection of Online Sexism",
author = "Feely, Weston and
Gupta, Prabhakar and
Mohanty, Manas Ranjan and
Chon, Timothy and
Kundu, Tuhin and
Singh, Vijit and
Atluri, Sandeep and
Roosta, Tanya and
Ghaderi, Viviane and
Schulam, Peter",
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-1.175/",
doi = "10.18653/v1/2023.semeval-1.175",
pages = "1260--1270",
abstract = "The web contains an abundance of user- generated content. While this content is useful for many applications, it poses many challenges due to the presence of offensive, biased, and overall toxic language. In this work, we present a system that identifies and classifies sexist content at different levels of granularity. Using transformer-based models, we explore the value of data augmentation, use of ensemble methods, and leverage in-context learning using foundation models to tackle the task. We evaluate the different components of our system both quantitatively and qualitatively. Our best systems achieve an F1 score of 0.84 for the binary classification task aiming to identify whether a given content is sexist or not and 0.64 and 0.47 for the two multi-class tasks that aim to identify the coarse and fine-grained types of sexism present in the given content respectively."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feely-etal-2023-qcon">
<titleInfo>
<title>QCon at SemEval-2023 Task 10: Data Augmentation and Model Ensembling for Detection of Online Sexism</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weston</namePart>
<namePart type="family">Feely</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prabhakar</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manas</namePart>
<namePart type="given">Ranjan</namePart>
<namePart type="family">Mohanty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Chon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tuhin</namePart>
<namePart type="family">Kundu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vijit</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Atluri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanya</namePart>
<namePart type="family">Roosta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="family">Ghaderi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Schulam</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>The web contains an abundance of user- generated content. While this content is useful for many applications, it poses many challenges due to the presence of offensive, biased, and overall toxic language. In this work, we present a system that identifies and classifies sexist content at different levels of granularity. Using transformer-based models, we explore the value of data augmentation, use of ensemble methods, and leverage in-context learning using foundation models to tackle the task. We evaluate the different components of our system both quantitatively and qualitatively. Our best systems achieve an F1 score of 0.84 for the binary classification task aiming to identify whether a given content is sexist or not and 0.64 and 0.47 for the two multi-class tasks that aim to identify the coarse and fine-grained types of sexism present in the given content respectively.</abstract>
<identifier type="citekey">feely-etal-2023-qcon</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.175</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.175/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1260</start>
<end>1270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QCon at SemEval-2023 Task 10: Data Augmentation and Model Ensembling for Detection of Online Sexism
%A Feely, Weston
%A Gupta, Prabhakar
%A Mohanty, Manas Ranjan
%A Chon, Timothy
%A Kundu, Tuhin
%A Singh, Vijit
%A Atluri, Sandeep
%A Roosta, Tanya
%A Ghaderi, Viviane
%A Schulam, Peter
%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 feely-etal-2023-qcon
%X The web contains an abundance of user- generated content. While this content is useful for many applications, it poses many challenges due to the presence of offensive, biased, and overall toxic language. In this work, we present a system that identifies and classifies sexist content at different levels of granularity. Using transformer-based models, we explore the value of data augmentation, use of ensemble methods, and leverage in-context learning using foundation models to tackle the task. We evaluate the different components of our system both quantitatively and qualitatively. Our best systems achieve an F1 score of 0.84 for the binary classification task aiming to identify whether a given content is sexist or not and 0.64 and 0.47 for the two multi-class tasks that aim to identify the coarse and fine-grained types of sexism present in the given content respectively.
%R 10.18653/v1/2023.semeval-1.175
%U https://aclanthology.org/2023.semeval-1.175/
%U https://doi.org/10.18653/v1/2023.semeval-1.175
%P 1260-1270
Markdown (Informal)
[QCon at SemEval-2023 Task 10: Data Augmentation and Model Ensembling for Detection of Online Sexism](https://aclanthology.org/2023.semeval-1.175/) (Feely et al., SemEval 2023)
ACL
- Weston Feely, Prabhakar Gupta, Manas Ranjan Mohanty, Timothy Chon, Tuhin Kundu, Vijit Singh, Sandeep Atluri, Tanya Roosta, Viviane Ghaderi, and Peter Schulam. 2023. QCon at SemEval-2023 Task 10: Data Augmentation and Model Ensembling for Detection of Online Sexism. In Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023), pages 1260–1270, Toronto, Canada. Association for Computational Linguistics.