"Define Your Terms" : Enhancing Efficient Offensive Speech Classification with Definition
This work addresses the challenge of resource scarcity in offensive speech classification for social media platforms, offering an incremental improvement in efficiency.
The paper tackled the problem of efficiently detecting offensive speech on social media by leveraging meta-learning and joint embeddings of labels and definitions, achieving at least 75% of the maximal F1-score with less than 10% of training data across four datasets.
The propagation of offensive content through social media channels has garnered attention of the research community. Multiple works have proposed various semantically related yet subtle distinct categories of offensive speech. In this work, we explore meta-earning approaches to leverage the diversity of offensive speech corpora to enhance their reliable and efficient detection. We propose a joint embedding architecture that incorporates the input's label and definition for classification via Prototypical Network. Our model achieves at least 75% of the maximal F1-score while using less than 10% of the available training data across 4 datasets. Our experimental findings also provide a case study of training strategies valuable to combat resource scarcity.