Learning Entity and Relation Embeddings with Entity Description for Knowledge Graph Completion

DOI

10.2991/icaita-18.2018.49How to use a DOI?

Keywords

knowledge graph completion; entity description; natural language processing

Abstract

With the growth of existing knowledge graph, the completion of knowledge graph has become a crucial problem. In this paper, we propose a novel model based on description-embodied knowledge representation learning framework, which is able to take advantages of both fact triples and entity description. Specifically, the relation projection is combined with description-embodied representation learning to learn entity and relation embeddings. Convolutional neural network and TransR are adopted to get the description-based and structure-based representation of entity and relation, respectively. We employ FB15K dataset generated from a large knowledge graph freebase, to evaluate the performances of the proposed model. Experimental results show that our proposed model greatly outperforms other existing baseline models.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shaozhi Dai
AU  - Yanchun Liang
AU  - Shuyan Liu
AU  - Ying Wang
AU  - Wenle Shao
AU  - Xixun Lin
AU  - Xiaoyue Feng
PY  - 2018/03
DA  - 2018/03
TI  - Learning Entity and Relation Embeddings with Entity Description for Knowledge Graph Completion
BT  - Proceedings of the 2018 2nd International Conference on Artificial Intelligence: Technologies and Applications (ICAITA 2018)
PB  - Atlantis Press
SP  - 194
EP  - 197
SN  - 1951-6851
UR  - https://doi.org/10.2991/icaita-18.2018.49
DO  - 10.2991/icaita-18.2018.49
ID  - Dai2018/03
ER  -