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

While Knowledge Graph Completion (KGC) on static facts is a matured field,Temporal Knowledge Graph Completion (TKGC), that incorporates validity timeinto static facts is still in its nascent stage. The KGC methods fall intomultiple categories including embedding-based, rule-based, GNN-based,pretrained Language Model based approaches. However, such dimensions have notbeen explored in TKG. To that end, we propose a novel temporal neuro-symbolicmodel, NeuSTIP, that performs link prediction and time interval prediction in aTKG. NeuSTIP learns temporal rules in the presence of the Allen predicates thatensure the temporal consistency between neighboring predicates in a given rule.We further design a unique scoring function that evaluates the confidence ofthe candidate answers while performing link prediction and time intervalprediction by utilizing the learned rules. Our empirical evaluation on two timeinterval based TKGC datasets suggests that our model outperformsstate-of-the-art models for both link prediction and the time intervalprediction task.

NeuSTIP: A Novel Neuro-Symbolic Model for Link and Time Prediction in Temporal Knowledge Graphs