Graph Reasoning with Context-Aware Linearization for Interpretable Fact Extraction and Verification

Neema Kotonya, Thomas Spooner, Daniele Magazzeni, Francesca Toni


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.
Anthology ID:
2021.fever-1.3
Volume:
Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER)
Month:
November
Year:
2021
Address:
Dominican Republic
Venues:
EMNLP | FEVER
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
21–30
Language:
URL:
https://aclanthology.org/2021.fever-1.3
DOI:
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.fever-1.3.pdf
Data
FEVERFEVEROUS