A Novel Encoder-Decoder Knowledge Graph Completion Model for Robot Brain

• Published in: Frontiers in neurorobotics Vol. 15; p. 674428
• Main Authors: Song, Yichen, Li, Aiping, Tu, Hongkui, Chen, Kai, Li, Chenchen
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 11.05.2021; Frontiers Media S.A
• Subjects: Artificial intelligence; Brain research; Cybernetics; Embedding; Graph representations; human-robot interaction; knowledge graph embedding; knowledge graph reasoning and completion; Knowledge representation; learning-based artificial intelligence; Methods; Neural networks; Neuroscience; robot intelligence; Robots; Semantics; human-robot interaction; robot intelligence; learning-based artificial intelligence; knowledge graph embedding; knowledge graph reasoning and completion
• ISSN: 1662-5218; 1662-5218
• DOI: 10.3389/fnbot.2021.674428

With the rapid development of artificial intelligence, Cybernetics, and other High-tech subject technology, robots have been made and used in increasing fields. And studies on robots 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 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 as 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 a gate mechanism to control the 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.