Work

UCL Machine Reading Group: Four Factor Framework For Fact Finding (HexaF)

Year: 2018

Type: conference-paper

Abstract: In this paper we describe our 2 nd 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.

Source: Fact Extraction and VERification Workshop (FEVER)

DOI: 10.18653/v1/w18-5515

Authors: Takuma Yoneda, Jeff Mitchell, Johannes Welbl, Pontus Stenetorp, Sebastian Riedel

Institutions: Toyota Technological Institute, University College London

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: European Commission, Horizon 2020 Framework Programme, Engineering and Physical Sciences Research Council

Awards: G4937468798, G5045220161, Scalable Understanding of Multilingual Media