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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Knowledge Graph Completion (KGC) aims to reason over known facts and infermissing links but achieves weak performances on those sparse Knowledge Graphs(KGs). Recent works introduce text information as auxiliary features or applygraph densification to alleviate this challenge, but suffer from problems ofineffectively incorporating structure features and injecting noisy triples. Inthis paper, we solve the sparse KGC from these two motivations simultaneouslyand handle their respective drawbacks further, and propose a plug-and-playunified framework VEM$^2$L over sparse KGs. The basic idea of VEM$^2$L is tomotivate a text-based KGC model and a structure-based KGC model to learn witheach other to fuse respective knowledge into unity. To exploit text andstructure features together in depth, we partition knowledge within models intotwo nonoverlapping parts: expressiveness ability on the training set andgeneralization ability upon unobserved queries. For the former, we motivatethese two text-based and structure-based models to learn from each other on thetraining sets. And for the generalization ability, we propose a novel knowledgefusion strategy derived by the Variational EM (VEM) algorithm, during which wealso apply a graph densification operation to alleviate the sparse graphproblem further. Our graph densification is derived by VEM algorithm. Due tothe convergence of EM algorithm, we guarantee the increase of likelihoodfunction theoretically with less being impacted by noisy injected triplesheavily. By combining these two fusion methods and graph densification, wepropose the VEM$^2$L framework finally. Both detailed theoretical evidence, aswell as qualitative experiments, demonstrates the effectiveness of our proposedframework.

VEM$^2$L: A Plug-and-play Framework for Fusing Text and Structure Knowledge on Sparse Knowledge Graph Completion