Published November 1, 2018 | Version v1

UCL Machine Reading Group: Four Factor Framework For Fact Finding,

  • 1. Toyota Technological Institute
  • 2. University College London

Description

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.

Files

hexaf.pdf

Files (173.7 kB)

Name Size
md5:a3a890d7c07a0ce7b3082a4e4ee50290
173.7 kB Preview Download

Additional details

Funding

European Commission
SUMMA - Scalable Understanding of Multilingual Media 688139