Improving Evidence Retrieval with Claim-Evidence Entailment

Fan Yang, Eduard Dragut, Arjun Mukherjee


Abstract
Claim verification is challenging because it requires first to find textual evidence and then apply claim-evidence entailment to verify a claim. Previous works evaluate the entailment step based on the retrieved evidence, whereas we hypothesize that the entailment prediction can provide useful signals for evidence retrieval, in the sense that if a sentence supports or refutes a claim, the sentence must be relevant. We propose a novel model that uses the entailment score to express the relevancy. Our experiments verify that leveraging entailment prediction improves ranking multiple pieces of evidence.
Anthology ID:
2021.ranlp-1.174
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
1553–1558
Language:
URL:
https://aclanthology.org/2021.ranlp-1.174
DOI:
Bibkey:
Cite (ACL):
Fan Yang, Eduard Dragut, and Arjun Mukherjee. 2021. Improving Evidence Retrieval with Claim-Evidence Entailment. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1553–1558, Held Online. INCOMA Ltd..
Cite (Informal):
Improving Evidence Retrieval with Claim-Evidence Entailment (Yang et al., RANLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2021.ranlp-1.174.pdf
Data
FEVER