@inproceedings{al-azzawi-etal-2023-nlp,
title = "{NLP}-{LTU} at {S}em{E}val-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset",
author = {Al-Azzawi, Sana and
Kov{\'a}cs, Gy{\"o}rgy and
Nilsson, Filip and
Adewumi, Tosin and
Liwicki, Marcus},
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-1.196/",
doi = "10.18653/v1/2023.semeval-1.196",
pages = "1421--1427",
abstract = "In this paper, we propose a methodology fortask 10 of SemEval23, focusing on detectingand classifying online sexism in social me-dia posts. The task is tackling a serious is-sue, as detecting harmful content on socialmedia platforms is crucial for mitigating theharm of these posts on users. Our solutionfor this task is based on an ensemble of fine-tuned transformer-based models (BERTweet,RoBERTa, and DeBERTa). To alleviate prob-lems related to class imbalance, and to improvethe generalization capability of our model, wealso experiment with data augmentation andsemi-supervised learning. In particular, fordata augmentation, we use back-translation, ei-ther on all classes, or on the underrepresentedclasses only. We analyze the impact of thesestrategies on the overall performance of thepipeline through extensive experiments. whilefor semi-supervised learning, we found thatwith a substantial amount of unlabelled, in-domain data available, semi-supervised learn-ing can enhance the performance of certainmodels. Our proposed method (for which thesource code is available on Github12) attainsan F 1-score of 0.8613 for sub-taskA, whichranked us 10th in the competition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="al-azzawi-etal-2023-nlp">
<titleInfo>
<title>NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sana</namePart>
<namePart type="family">Al-Azzawi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">György</namePart>
<namePart type="family">Kovács</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Nilsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tosin</namePart>
<namePart type="family">Adewumi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcus</namePart>
<namePart type="family">Liwicki</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>In this paper, we propose a methodology fortask 10 of SemEval23, focusing on detectingand classifying online sexism in social me-dia posts. The task is tackling a serious is-sue, as detecting harmful content on socialmedia platforms is crucial for mitigating theharm of these posts on users. Our solutionfor this task is based on an ensemble of fine-tuned transformer-based models (BERTweet,RoBERTa, and DeBERTa). To alleviate prob-lems related to class imbalance, and to improvethe generalization capability of our model, wealso experiment with data augmentation andsemi-supervised learning. In particular, fordata augmentation, we use back-translation, ei-ther on all classes, or on the underrepresentedclasses only. We analyze the impact of thesestrategies on the overall performance of thepipeline through extensive experiments. whilefor semi-supervised learning, we found thatwith a substantial amount of unlabelled, in-domain data available, semi-supervised learn-ing can enhance the performance of certainmodels. Our proposed method (for which thesource code is available on Github12) attainsan F 1-score of 0.8613 for sub-taskA, whichranked us 10th in the competition.</abstract>
<identifier type="citekey">al-azzawi-etal-2023-nlp</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.196</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.196/</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1421</start>
<end>1427</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset
%A Al-Azzawi, Sana
%A Kovács, György
%A Nilsson, Filip
%A Adewumi, Tosin
%A Liwicki, Marcus
%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 al-azzawi-etal-2023-nlp
%X In this paper, we propose a methodology fortask 10 of SemEval23, focusing on detectingand classifying online sexism in social me-dia posts. The task is tackling a serious is-sue, as detecting harmful content on socialmedia platforms is crucial for mitigating theharm of these posts on users. Our solutionfor this task is based on an ensemble of fine-tuned transformer-based models (BERTweet,RoBERTa, and DeBERTa). To alleviate prob-lems related to class imbalance, and to improvethe generalization capability of our model, wealso experiment with data augmentation andsemi-supervised learning. In particular, fordata augmentation, we use back-translation, ei-ther on all classes, or on the underrepresentedclasses only. We analyze the impact of thesestrategies on the overall performance of thepipeline through extensive experiments. whilefor semi-supervised learning, we found thatwith a substantial amount of unlabelled, in-domain data available, semi-supervised learn-ing can enhance the performance of certainmodels. Our proposed method (for which thesource code is available on Github12) attainsan F 1-score of 0.8613 for sub-taskA, whichranked us 10th in the competition.
%R 10.18653/v1/2023.semeval-1.196
%U https://aclanthology.org/2023.semeval-1.196/
%U https://doi.org/10.18653/v1/2023.semeval-1.196
%P 1421-1427
Markdown (Informal)
[NLP-LTU at SemEval-2023 Task 10: The Impact of Data Augmentation and Semi-Supervised Learning Techniques on Text Classification Performance on an Imbalanced Dataset](https://aclanthology.org/2023.semeval-1.196/) (Al-Azzawi et al., SemEval 2023)
ACL