English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Real-world fact verification task aims to verify the factuality of a claim byretrieving evidence from the source document. The quality of the retrievedevidence plays an important role in claim verification. Ideally, the retrievedevidence should be faithful (reflecting the model's decision-making process inclaim verification) and plausible (convincing to humans), and can improve theaccuracy of verification task. Although existing approaches leverage thesimilarity measure of semantic or surface form between claims and documents toretrieve evidence, they all rely on certain heuristics that prevent them fromsatisfying all three requirements. In light of this, we propose a factverification model named ReRead to retrieve evidence and verify claim that: (1)Train the evidence retriever to obtain interpretable evidence (i.e.,faithfulness and plausibility criteria); (2) Train the claim verifier torevisit the evidence retrieved by the optimized evidence retriever to improvethe accuracy. The proposed system is able to achieve significant improvementsupon best-reported models under different settings.

Read it Twice: Towards Faithfully Interpretable Fact Verification by Revisiting Evidence