BaIT: Barometer for Information Trustworthiness

no code implementations • 15 Jun 2022 • Oisín Nolan, Jeroen van Mourik, Callum Rhys Tilbury

This paper presents a new approach to the FNC-1 fake news classification task which involves employing pre-trained encoder models from similar NLP tasks, namely sentence similarity and natural language inference, and two neural network architectures using this approach are proposed.

Data Augmentation Natural Language Inference +4