Enhancing social network hate detection using back translation and GPT-3 augmentations during training and test-time

Open Webpage

Seffi Cohen, Dan Presil, Or Katz, Ofir Arbili, Shvat Messica, Lior Rokach

Published: 01 Jan 2023, Last Modified: 06 Feb 2025Inf. Fusion 2023EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Apply Test-Time Augmentation in NLP to improve hate speech detection.•Enhance augmentation quality with a selection method to filter unsuitable ones.•Merge DeBERTa, back-translation & GPT-3 to boost hate speech detection.•Manage hate speech complexities - effectively detects slang & implicit language.