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

Knowledge graphs (KGs), as structured representations of real world facts,are intelligent databases incorporating human knowledge that can help machineimitate the way of human problem solving. However, KGs are usually huge andthere are inevitably missing facts in KGs, thus undermining applications suchas question answering and recommender systems that are based on knowledge graphreasoning. Link prediction for knowledge graphs is the task aiming to completemissing facts by reasoning based on the existing knowledge. Two main streams ofresearch are widely studied: one learns low-dimensional embeddings for entitiesand relations that can explore latent patterns, and the other gains goodinterpretability by mining logical rules. Unfortunately, the heterogeneity ofmodern KGs that involve entities and relations of various types is not wellconsidered in the previous studies. In this paper, we propose DegreEmbed, amodel that combines embedding-based learning and logic rule mining forinferring on KGs. Specifically, we study the problem of predicting missinglinks in heterogeneous KGs from the perspective of the degree of nodes.Experimentally, we demonstrate that our DegreEmbed model outperforms thestate-of-the-art methods on real world datasets and the rules mined by ourmodel are of high quality and interpretability.

DegreEmbed: incorporating entity embedding into logic rule learning for knowledge graph reasoning