Abstract
We present a multi-task learning model that leverages large amount of textual information from existing datasets to improve stance prediction. In particular, we utilize multiple NLP tasks under both unsupervised and supervised settings for the target stance prediction task. Our model obtains state-of-the-art performance on a public benchmark dataset, Fake News Challenge, outperforming current approaches by a wide margin.- Anthology ID:
- D19-6603
- Volume:
- Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- James Thorne, Andreas Vlachos, Oana Cocarascu, Christos Christodoulopoulos, Arpit Mittal
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 13–19
- Language:
- URL:
- https://aclanthology.org/D19-6603
- DOI:
- 10.18653/v1/D19-6603
- Cite (ACL):
- Wei Fang, Moin Nadeem, Mitra Mohtarami, and James Glass. 2019. Neural Multi-Task Learning for Stance Prediction. In Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER), pages 13–19, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Neural Multi-Task Learning for Stance Prediction (Fang et al., 2019)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/D19-6603.pdf