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

Large-scale knowledge graphs provide structured representations of humanknowledge. However, as it is impossible to collect all knowledge, knowledgegraphs are usually incomplete. Reasoning based on existing facts paves a way todiscover missing facts. In this paper, we study the problem of learning logicalrules for reasoning on knowledge graphs for completing missing factualtriplets. Learning logical rules equips a model with strong interpretability aswell as the ability to generalize to similar tasks. We propose a model able tofully use training data which also considers multi-target scenarios. Inaddition, considering the deficiency in evaluating the performance of modelsand the quality of mined rules, we further propose two novel indicators to helpwith the problem. Experimental results empirically demonstrate that our modeloutperforms state-of-the-art methods on five benchmark datasets. The resultsalso prove the effectiveness of the indicators.

An original model for multi-target learning of logical rules for knowledge graph reasoning