UCL Machine Reading Group: Four Factor Framework For Fact Finding (HexaF)
Takuma Yoneda, Jeff Mitchell, Johannes Welbl, Pontus Stenetorp, Sebastian Riedel
Abstract
In this paper we describe our 2nd place FEVER shared-task system that achieved a FEVER score of 62.52% on the provisional test set (without additional human evaluation), and 65.41% on the development set. Our system is a four stage model consisting of document retrieval, sentence retrieval, natural language inference and aggregation. Retrieval is performed leveraging task-specific features, and then a natural language inference model takes each of the retrieved sentences paired with the claimed fact. The resulting predictions are aggregated across retrieved sentences with a Multi-Layer Perceptron, and re-ranked corresponding to the final prediction.- Anthology ID:
- W18-5515
- Volume:
- Proceedings of the First Workshop on Fact Extraction and VERification (FEVER)
- Month:
- November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- James Thorne, Andreas Vlachos, Oana Cocarascu, Christos Christodoulopoulos, Arpit Mittal
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 97–102
- Language:
- URL:
- https://aclanthology.org/W18-5515
- DOI:
- 10.18653/v1/W18-5515
- Cite (ACL):
- Takuma Yoneda, Jeff Mitchell, Johannes Welbl, Pontus Stenetorp, and Sebastian Riedel. 2018. UCL Machine Reading Group: Four Factor Framework For Fact Finding (HexaF). In Proceedings of the First Workshop on Fact Extraction and VERification (FEVER), pages 97–102, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- UCL Machine Reading Group: Four Factor Framework For Fact Finding (HexaF) (Yoneda et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/W18-5515.pdf