UnifEE: Unified Evidence Extraction for Fact Verification

Nan Hu, Zirui Wu, Yuxuan Lai, Chen Zhang, Yansong Feng


Abstract
FEVEROUS is a fact extraction and verification task that requires systems to extract evidence of both sentences and table cells from a Wikipedia dump, then predict the veracity of the given claim accordingly. Existing works extract evidence in the two formats separately, ignoring potential connections between them. In this paper, we propose a Unified Evidence Extraction model (UnifEE), which uses a mixed evidence graph to extract the evidence in both formats. With the carefully-designed unified evidence graph, UnifEE allows evidence interactions among all candidates in both formats at similar granularity. Experiments show that, with information aggregated from related evidence candidates in the fusion graph, UnifEE can make better decisions about which evidence should be kept, especially for claims requiring multi-hop reasoning or a combination of tables and texts. Thus it outperforms all previous evidence extraction methods and brings significant improvement in the subsequent claim verification step.
Anthology ID:
2023.eacl-main.82
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Andreas Vlachos, Isabelle Augenstein
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1150–1160
Language:
URL:
https://aclanthology.org/2023.eacl-main.82
DOI:
10.18653/v1/2023.eacl-main.82
Bibkey:
Cite (ACL):
Nan Hu, Zirui Wu, Yuxuan Lai, Chen Zhang, and Yansong Feng. 2023. UnifEE: Unified Evidence Extraction for Fact Verification. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pages 1150–1160, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
UnifEE: Unified Evidence Extraction for Fact Verification (Hu et al., EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-main.82.pdf
Video:
 https://aclanthology.org/2023.eacl-main.82.mp4