UL \& UM6P at SemEval-2023 Task 10: Semi-Supervised Multi-task Learning for Explainable Detection of Online Sexism

Lamsiyah, Salima; El Mahdaouy, Abdelkader; Alami, Hamza; Berrada, Ismail; Schommer, Christoph

doi:10.18653/v1/2023.semeval-1.88

Reference : UL \& UM6P at SemEval-2023 Task 10: Semi-Supervised Multi-task Learning for Explainab...


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/55990

Title :	UL \& UM6P at SemEval-2023 Task 10: Semi-Supervised Multi-task Learning for Explainable Detection of Online Sexism
Language :	English
Author, co-author :	Lamsiyah, Salima [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)]
	El Mahdaouy, Abdelkader [> >]
	Alami, Hamza [> >]
	Berrada, Ismail [> >]
	Schommer, Christoph [University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)]
Publication date :	2023
Main document title :	Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
Publisher :	Association for Computational Linguistics
Pages :	644--650
Peer reviewed :	Yes
City :	Toronto, Canada
Event name :	The 61st Annual Meeting of the Association for Computational Linguistics
Event date :	9-14 July 2023
Abstract :	[en] This paper introduces our participating system to the Explainable Detection of Online Sexism (EDOS) SemEval-2023 - Task 10: Explainable Detection of Online Sexism. The EDOS shared task covers three hierarchical sub-tasks for sexism detection, coarse-grained and fine-grained categorization. We have investigated both single-task and multi-task learning based on RoBERTa transformer-based language models. For improving the results, we have performed further pre-training of RoBERTa on the provided unlabeled data. Besides, we have employed a small sample of the unlabeled data for semi-supervised learning using the minimum class-confusion loss. Our system has achieved macro F1 scores of 82.25\textbackslash\%, 67.35\textbackslash\%, and 49.8\textbackslash\% on Tasks A, B, and C, respectively.
Permalink :	http://hdl.handle.net/10993/55990
DOI :	10.18653/v1/2023.semeval-1.88
Other URL :	https://aclanthology.org/2023.semeval-1.88

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Limited access	2023.semeval-1.88.pdf		Publisher postprint	169.38 kB	Request a copy

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices