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

Translational distance-based knowledge graph embedding has shown progressiveimprovements on the link prediction task, from TransE to the lateststate-of-the-art RotatE. However, N-1, 1-N and N-N predictions still remainchallenging. In this work, we propose a novel translational distance-basedapproach for knowledge graph link prediction. The proposed method includestwo-folds, first we extend the RotatE from 2D complex domain to high dimensionspace with orthogonal transforms to model relations for better modelingcapacity. Second, the graph context is explicitly modeled via two directedcontext representations. These context representations are used as part of thedistance scoring function to measure the plausibility of the triples duringtraining and inference. The proposed approach effectively improves predictionaccuracy on the difficult N-1, 1-N and N-N cases for knowledge graph linkprediction task. The experimental results show that it achieves betterperformance on two benchmark data sets compared to the baseline RotatE,especially on data set (FB15k-237) with many high in-degree connection nodes.

Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding