Abstract
The inability to correctly resolve rumours circulating online can have harmful real-world consequences. We present a method for incorporating model and data uncertainty estimates into natural language processing models for automatic rumour verification. We show that these estimates can be used to filter out model predictions likely to be erroneous so that these difficult instances can be prioritised by a human fact-checker. We propose two methods for uncertainty-based instance rejection, supervised and unsupervised. We also show how uncertainty estimates can be used to interpret model performance as a rumour unfolds.- Anthology ID:
- 2020.acl-main.623
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6964–6981
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.623
- DOI:
- 10.18653/v1/2020.acl-main.623
- Cite (ACL):
- Elena Kochkina and Maria Liakata. 2020. Estimating predictive uncertainty for rumour verification models. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6964–6981, Online. Association for Computational Linguistics.
- Cite (Informal):
- Estimating predictive uncertainty for rumour verification models (Kochkina & Liakata, ACL 2020)
- PDF:
- https://preview.aclanthology.org/landing_page/2020.acl-main.623.pdf
- Code
- kochkinaelena/Uncertainty4VerificationModels