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

Learning good representations on multi-relational graphs is essential toknowledge base completion (KBC). In this paper, we propose a newself-supervised training objective for multi-relational graph representationlearning, via simply incorporating relation prediction into the commonly used1vsAll objective. The new training objective contains not only terms forpredicting the subject and object of a given triple, but also a term forpredicting the relation type. We analyse how this new objective impactsmulti-relational learning in KBC: experiments on a variety of datasets andmodels show that relation prediction can significantly improve entity ranking,the most widely used evaluation task for KBC, yielding a 6.1% increase in MRRand 9.9% increase in Hits@1 on FB15k-237 as well as a 3.1% increase in MRR and3.4% in Hits@1 on Aristo-v4. Moreover, we observe that the proposed objectiveis especially effective on highly multi-relational datasets, i.e. datasets witha large number of predicates, and generates better representations when largerembedding sizes are used.

Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations