Graph reasoning with context-aware linearization for interpretable fact extraction and verification
File(s)
Published version
Author(s)
Kotonya, Neema
Spooner, Thomas
Magazzeni, Daniele
Toni, Francesca
Type
Conference Paper
Abstract
This paper presents an end-to-end system for fact extraction and verification using textual and tabular evidence, the performance of which we demonstrate on the FEVEROUS dataset. We experiment with both a multi-task learning paradigm to jointly train a graph attention network for both the task of evidence extraction and veracity prediction, as well as a single objective graph model for solely learning veracity prediction and separate evidence extraction. In both instances, we employ a framework for per-cell linearization of tabular evidence, thus allowing us to treat evidence from tables as sequences. The templates we employ for linearizing tables capture the context as well as the content of table data. We furthermore provide a case study to show the interpretability our approach. Our best performing system achieves a FEVEROUS score of 0.23 and 53% label accuracy on the blind test data.
Date Issued
2021-11-01
Date Acceptance
2021-09-13
Citation
Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), 2021, pp.21-30
Publisher
Association for Computational Linguistics
Start Page
21
End Page
30
Journal / Book Title
Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)
Copyright Statement
© 2021 Association for Computational Linguistics. ACL materials are available to the general public on the terms of the Creative Commons 4.0 BY (Attribution) license (https://creativecommons.org/licenses/by/4.0/)
License URL
Sponsor
JPMorgan Chase Bank, N.A.
Identifier
https://aclanthology.org/2021.fever-1.3
Grant Number
COLAR_P86244
Source
FEVER 2021
Publication Status
Published
Start Date
2021-11-01
Coverage Spatial
Dominican Republic