RT Conference Proceedings
T1 I2C-Huelva at SemEval-2023 Task 10: Ensembling Transformers Models for the Detection of Online Sexism
A1 Fudulu, Lavinia Felicia
A1 Rodríguez Tenorio, Alberto
A1 Pachón Álvarez, Victoria
A1 Mata Vázquez, Jacinto
AB This work details our approach foraddressing Tasks A and B of the Semeval2023 Task 10: Explainable Detection ofOnline Sexism (EDOS). For Task A asimple ensemble based of majority votesystem was presented. To build ourproposal, first a review of transformers wascarried out and the 3 best performingmodels were selected to be part of theensemble. Next, for these models, the besthyperpameters were searched using areduced data set. Finally, we trained thesemodels using more data. During thedevelopment phase, our ensemble systemachieved an f1-score of 0.8403. For task B,we developed a model based on thedeBERTa transformer, utilizing thehyperparameters identified for task A.During the development phase, ourproposed model attained an f1-score of0.6467. Overall, our methodologydemonstrates an effective approach to thetasks, leveraging advanced machinelearning techniques and hyperparameterssearches to achieve high performance indetecting and classifying instances ofsexism in online text.
PB Association for Computational Linguistics
YR 2023
FD 2023-07
LK https://hdl.handle.net/10272/24379
UL https://hdl.handle.net/10272/24379
LA eng
NO Fudulu, L.F., Rodriguez Tenorio, A., Pachón Álvarez, V., & Mata Vázquez, J. (2023). I2C-Huelva at SemEval-2023 Task 10: Ensembling Transformers Models for the Detection of Online Sexism. In Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023) (pp. 763–769). Proceedings of the The 17th International Workshop on Semantic Evaluation (SemEval-2023). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.semeval-1.105
NO This paper is part of the I+D+i Project titled “Conspiracy Theories and hate speech online: Comparison of patterns in narratives and social networks about COVID-19, immigrants, refugees and LGBTI people [NON-CONSPIRA-HATE!]”,PID2021-123983OB-I00, funded by MCIN/AEI/10.13039/501100011033/ and by “ERDF A way of making Europe”.
DS Repositorio Institucional de la Universidad de Huelva
RD 1 jun 2026