Full text

Turn on search term navigation

© 2021. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

With the rapid development of artificial intelligence, Cybernetics and other High-tech subject technology, robots have been made and used in increasing fields, and have attracted growing research interests from different communities. The knowledge graph can act as the brain of a robot and provide intelligence, to support the interaction between the robot and the human beings. Although the large-scale knowledge graphs contain a large amount of information, they are still incomplete compared with the real world knowledge. Most existing methods for knowledge graph completion focus on entity representation learning. However, the importance of relation representation learning is ignored, as well the cross-interaction between entities and relations. In this paper, we propose an encoder-decoder model which embeds the interaction between entities and relations and adds gate mechanism to control attention mechanism. Experimental results show that our method achieves better link prediction performance than state-of-the-art embedding models on two benchmark datasets, WN18RR and FB15k-237.

Details

Title
A Novel Encoder-Decoder Knowledge Graph Completion Model for Robot Brain
Author
Song, Yichen; Li, Aiping; Tu, Hongkui; Chen, Kai; Li, Chenchen
Section
ORIGINAL RESEARCH article
Publication year
2021
Publication date
May 11, 2021
Publisher
Frontiers Research Foundation
e-ISSN
16625218
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2525213897
Copyright
© 2021. This work is licensed under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.