Improving Evidence Retrieval for Automated Explainable Fact-Checking

Chris Samarinas, Wynne Hsu, Mong Li Lee


Abstract
Automated fact-checking on a large-scale is a challenging task that has not been studied systematically until recently. Large noisy document collections like the web or news articles make the task more difficult. We describe a three-stage automated fact-checking system, named Quin+, using evidence retrieval and selection methods. We demonstrate that using dense passage representations leads to much higher evidence recall in a noisy setting. We also propose two sentence selection approaches, an embedding-based selection using a dense retrieval model, and a sequence labeling approach for context-aware selection. Quin+ is able to verify open-domain claims using results from web search engines.
Anthology ID:
2021.naacl-demos.10
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
84–91
Language:
URL:
https://aclanthology.org/2021.naacl-demos.10
DOI:
10.18653/v1/2021.naacl-demos.10
Bibkey:
Cite (ACL):
Chris Samarinas, Wynne Hsu, and Mong Li Lee. 2021. Improving Evidence Retrieval for Automated Explainable Fact-Checking. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstrations, pages 84–91, Online. Association for Computational Linguistics.
Cite (Informal):
Improving Evidence Retrieval for Automated Explainable Fact-Checking (Samarinas et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-demos.10.pdf
Supplementary:
 2021.naacl-demos.10.Supplementary.txt
Video:
 https://aclanthology.org/2021.naacl-demos.10.mp4
Code
 algoprog/Quin
Data
FEVERMS MARCOMultiNLISNLISciFact