The Art of Embedding Fusion: Optimizing Hate Speech DetectionDownload PDF

01 Mar 2023 (modified: 25 Nov 2024)Submitted to Tiny Papers @ ICLR 2023Readers: Everyone
Keywords: Hate Speech, Embeddings, NLP, Detection, Social Computing
TL;DR: The work evaluates different embedding combination methods for hate speech detection.
Abstract: Hate speech detection is a challenging natural language processing task that requires capturing linguistic and contextual nuances. Pre-trained language models (PLMs) offer rich semantic representations of text that can improve this task. However there is still limited knowledge about ways to effectively combine representations across PLMs and leverage their complementary strengths. In this work, we shed light on various combination techniques for several PLMs and comprehensively analyze their effectiveness. Our findings show that combining embeddings leads to slight improvements but at a high computational cost and the choice of combination has marginal effect on the final outcome.
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/the-art-of-embedding-fusion-optimizing-hate/code)
9 Replies

Loading