"LexiFuse+: A Unified One-Class Solution for Imbalanced Short-Text Clas" by Saugata Bose and Guoxin Su
Introducing LexiFuse+: a semi-supervised model merging lexicon features, BERT transfer learning, and one-class classifiers to detect anomalous content in short texts. It tackles challenges of informal text and imbalanced datasets, excelling in hate speech detection. By leveraging one-class classifiers in a fully deep fine-tuned network trained with unlabeled data, LexiFuse+ surpasses base models.
Source: uow.edu.au