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
- 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)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.naacl-demos.10.pdf
- Code
- algoprog/Quin
- Data
- FEVER, MS MARCO, MultiNLI, SNLI, SciFact