Combating high variance in Data-Scarce Implicit Hate Speech Classification
This addresses the challenge of detecting implicit hate speech in NLP, which is often overlooked by existing methods, though it appears incremental as it builds on transformer-based approaches.
The paper tackles the problem of high variance in implicit hate speech classification due to data scarcity by developing a novel RoBERTa-based model with optimization and regularization techniques, achieving state-of-the-art performance.
Hate speech classification has been a long-standing problem in natural language processing. However, even though there are numerous hate speech detection methods, they usually overlook a lot of hateful statements due to them being implicit in nature. Developing datasets to aid in the task of implicit hate speech classification comes with its own challenges; difficulties are nuances in language, varying definitions of what constitutes hate speech, and the labor-intensive process of annotating such data. This had led to a scarcity of data available to train and test such systems, which gives rise to high variance problems when parameter-heavy transformer-based models are used to address the problem. In this paper, we explore various optimization and regularization techniques and develop a novel RoBERTa-based model that achieves state-of-the-art performance.