Modeling Entity Knowledge for Fact Verification

Yang Liu, Chenguang Zhu, Michael Zeng


Abstract
Fact verification is a challenging task of identifying the truthfulness of given claims based on the retrieval of relevant evidence texts. Many claims require understanding and reasoning over external entity information for precise verification. In this paper, we propose a novel fact verification model using entity knowledge to enhance its performance. We retrieve descriptive text from Wikipedia for each entity, and then encode these descriptions by a smaller lightweight network to be fed into the main verification model. Furthermore, we boost model performance by adopting and predicting the relatedness between the claim and each evidence as additional signals. We demonstrate experimentally on a large-scale benchmark dataset FEVER that our framework achieves competitive results with a FEVER score of 72.89% on the test set.
Anthology ID:
2021.fever-1.6
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:
50–59
Language:
URL:
https://aclanthology.org/2021.fever-1.6
DOI:
10.18653/v1/2021.fever-1.6
Bibkey:
Cite (ACL):
Yang Liu, Chenguang Zhu, and Michael Zeng. 2021. Modeling Entity Knowledge for Fact Verification. In Proceedings of the Fourth Workshop on Fact Extraction and VERification (FEVER), pages 50–59, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Modeling Entity Knowledge for Fact Verification (Liu et al., FEVER 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/update-css-js/2021.fever-1.6.pdf
Data
FEVER