Knowledge graph embedding by dynamic translation

Chang, Liang and Zhu, Manli and Gu, Tianlong and Bin, Chenzhong and Qian, Junyan and Zhang, Ji (2017) Knowledge graph embedding by dynamic translation. IEEE Access, 5 (3). pp. 20898-20907.

[img]
Preview
Text (Published Version)
Published version.pdf

Download (7MB) | Preview

Abstract

Knowledge graph embedding aims at representing entities and relations in a knowledge graph as dense, low-dimensional and real-valued vectors. It can efficiently measure semantic correlations of entities and relations in knowledge graphs, and improve the performance of knowledge acquisition, fusion and inference. Among various embedding models appeared in recent years, the translation-based models such as TransE, TransH, TransR and TranSparse achieve state-of-the-art performance. However, the translation principle applied in these models is too strict and can not deal with complex entities and relations very well. In this paper, by introducing parameter vectors into the translation principle which treats each relation as a translation from the head entity to the tail entity, we propose a novel dynamic translation principle which supports flexible translation between the embeddings of entities and relations. We use this principle to improve the TransE, TransR and TranSparse models respectively and build new models named TransE-DT, TransR-DT and TranSparse-DT correspondingly. Experimental results show that our dynamic translation principle achieves great improvement in both the link prediction task and the triple classification task.


Statistics for USQ ePrint 36144
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Faculty/School / Institute/Centre: Historic - Faculty of Health, Engineering and Sciences - School of Agricultural, Computational and Environmental Sciences (1 Jul 2013 - 5 Sep 2019)
Faculty/School / Institute/Centre: Historic - Faculty of Health, Engineering and Sciences - School of Agricultural, Computational and Environmental Sciences (1 Jul 2013 - 5 Sep 2019)
Date Deposited: 20 Sep 2019 01:12
Last Modified: 25 Sep 2019 04:18
Uncontrolled Keywords: semantics, natural language processing systems, word representations
Fields of Research (2008): 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
Identification Number or DOI: https://doi.org/10.1109/ACCESS.2017.2759139
URI: http://eprints.usq.edu.au/id/eprint/36144

Actions (login required)

View Item Archive Repository Staff Only