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

The problem of knowledge graph (KG) reasoning has been widely explored bytraditional rule-based systems and more recently by knowledge graph embeddingmethods. While logical rules can capture deterministic behavior in a KG theyare brittle and mining ones that infer facts beyond the known KG ischallenging. Probabilistic embedding methods are effective in capturing globalsoft statistical tendencies and reasoning with them is computationallyefficient. While embedding representations learned from rich training data areexpressive, incompleteness and sparsity in real-world KGs can impact theireffectiveness. We aim to leverage the complementary properties of both methodsto develop a hybrid model that learns both high-quality rules and embeddingssimultaneously. Our method uses a cross feedback paradigm wherein, an embeddingmodel is used to guide the search of a rule mining system to mine rules andinfer new facts. These new facts are sampled and further used to refine theembedding model. Experiments on multiple benchmark datasets show theeffectiveness of our method over other competitive standalone and hybridbaselines. We also show its efficacy in a sparse KG setting and finally explorethe connection with negative sampling.

A Hybrid Model for Learning Embeddings and Logical Rules Simultaneously from Knowledge Graphs