Semantic Apparatus – Evidence Inference Networks for Interpretable Claim Verification

Cited by Lee Sonogan

Our end-to-end hierarchical attention networks for claim verification. |  Download Scientific Diagram

Abstract by Lianwei Wu, Yuan Rao, Ling Sun, Wangbo He

Existing approaches construct appropriate interaction mod-els to explore semantic conflicts between claims and relevant articles, which provides practical solutions for interpretable claim verification. However, these conflicts are not necessarily all about questioning the false part of claims, which makes considerable semantic conflicts difficult to be used as evidence to explain the results of claim verification, especially those that cannot identify the core semantics of claims. In this paper, we propose evidence inference networks (EVIN), which focus on the conflicts questioning the core semantics of claims and serve as evidence for interpretable claim verification. Specifi-
cally, EVIN first captures the core semantic segments of claims and the users’ principal opinions in relevant articles. Then, it finely-grained identifies the semantic conflicts contained in each relevant article from these opinions. Finally, EVIN con-structs coherence modeling to match the conflicts that queries the core semantic fragments of claims as explainable evidence. Experiments on two widely used datasets demonstrate that
EVIN not only achieves satisfactory performance but also provides explainable evidence for end-users.

Publication: (Peer-Reviewed Journal)

Pub Date: 2021 Doi:

Keywords: Evidence Inference, Semantic Networks, Interpretable Claim, Conflict Verification (Plenty more sections and references in this research article)

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.