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

Recent studies constructing direct interactions between the claim and eachsingle user response (a comment or a relevant article) to capture evidence haveshown remarkable success in interpretable claim verification. Owing todifferent single responses convey different cognition of individual users(i.e., audiences), the captured evidence belongs to the perspective ofindividual cognition. However, individuals' cognition of social things is notalways able to truly reflect the objective. There may be one-sided or biasedsemantics in their opinions on a claim. The captured evidence correspondinglycontains some unobjective and biased evidence fragments, deteriorating taskperformance. In this paper, we propose a Dual-view model based on the views ofCollective and Individual Cognition (CICD) for interpretable claimverification. From the view of the collective cognition, we not only capturethe word-level semantics based on individual users, but also focus onsentence-level semantics (i.e., the overall responses) among all users andadjust the proportion between them to generate global evidence. From the viewof individual cognition, we select the top-$k$ articles with high degree ofdifference and interact with the claim to explore the local key evidencefragments. To weaken the bias of individual cognition-view evidence, we deviseinconsistent loss to suppress the divergence between global and local evidencefor strengthening the consistent shared evidence between the both. Experimentson three benchmark datasets confirm that CICD achieves state-of-the-artperformance.

Unified Dual-view Cognitive Model for Interpretable Claim Verification