Alexa at SemEval-2023 Task 10: Ensemble Modeling of DeBERTa and BERT Variations for Identifying Sexist Text

Abstract

This study presents an ensemble approach for detecting sexist text in the context of the Semeval-2023 task 10. Our approach leverages 18 models, including DeBERTa-v3-base models with different input sequence lengths, a BERT-based model trained on identifying hate speech, and three more models pre-trained on the task’s unlabeled data with varying input lengths. The results of our framework on the development set show an f1-score of 84.92% and on the testing set 84.55%, effectively demonstrating the strength of the ensemble approach in getting accurate results.