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

Real-world knowledge graphs (KG) are mostly incomplete. The problem ofrecovering missing relations, called KG completion, has recently become anactive research area. Knowledge graph (KG) embedding, a low-dimensionalrepresentation of entities and relations, is the crucial technique for KGcompletion. Convolutional neural networks in models such as ConvE, SACN,InteractE, and RGCN achieve recent successes. This paper takes a differentarchitectural view and proposes ComDensE which combines relation-aware andcommon features using dense neural networks. In the relation-aware featureextraction, we attempt to create relational inductive bias by applying anencoding function specific to each relation. In the common feature extraction,we apply the common encoding function to all input embeddings. These encodingfunctions are implemented using dense layers in ComDensE. ComDensE achieves thestate-of-the-art performance in the link prediction in terms of MRR, HIT@1 onFB15k-237 and HIT@1 on WN18RR compared to the previous baseline approaches. Weconduct an extensive ablation study to examine the effects of therelation-aware layer and the common layer of the ComDensE. Experimental resultsillustrate that the combined dense architecture as implemented in ComDensEachieves the best performance.

ComDensE : Combined Dense Embedding of Relation-aware and Common Features for Knowledge Graph Completion