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

Concept relatedness estimation (CRE) aims to determine whether two givenconcepts are related. Existing methods only consider the pairwise relationshipbetween concepts, while overlooking the higher-order relationship that could beencoded in a concept-level graph structure. We discover that this underlyinggraph satisfies a set of intrinsic properties of CRE, including reflexivity,commutativity, and transitivity. In this paper, we formalize the CRE propertiesand introduce a graph structure named ConcreteGraph. To address the datascarcity issue in CRE, we introduce a novel data augmentation approach tosample new concept pairs from the graph. As it is intractable for dataaugmentation to fully capture the structural information of the ConcreteGraphdue to a large amount of potential concept pairs, we further introduce a novelGraph Component Contrastive Learning framework to implicitly learn the completestructure of the ConcreteGraph. Empirical results on three datasets showsignificant improvement over the state-of-the-art model. Detailed ablationstudies demonstrate that our proposed approach can effectively capture thehigh-order relationship among concepts.

Graph Component Contrastive Learning for Concept Relatedness Estimation