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

Learning the embeddings of knowledge graphs (KG) is vital in artificialintelligence, and can benefit various downstream applications, such asrecommendation and question answering. In recent years, many research effortshave been proposed for knowledge graph embedding (KGE). However, most previousKGE methods ignore the semantic similarity between the related entities andentity-relation couples in different triples since they separately optimizeeach triple with the scoring function. To address this problem, we propose asimple yet efficient contrastive learning framework for tensor decompositionbased (TDB) KGE, which can shorten the semantic distance of the relatedentities and entity-relation couples in different triples and thus improve theperformance of KGE. We evaluate our proposed method on three standard KGEdatasets: WN18RR, FB15k-237 and YAGO3-10. Our method can yield some newstate-of-the-art results, achieving 51.2% MRR, 46.8% Hits@1 on the WN18RRdataset, 37.8% MRR, 28.6% Hits@1 on FB15k-237 dataset, and 59.1% MRR, 51.8%Hits@1 on the YAGO3-10 dataset.

KGE-CL: Contrastive Learning of Tensor Decomposition Based Knowledge Graph Embeddings