Share Email Print
cover

Proceedings Paper

Entity relationship extraction optimization based on entity recognition
Author(s): Yanru Zhong; Zhaorong He; Leixian Zhao; Chaohao Jiang; Xiaonan Luo
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Chinese entity relationship is usually stored in the form of a triple, usually based on dependent on its syntactic and semantic role labeling way of information extraction, the method to extract the entities may be greatly influenced by noise, this paper USES neural network is optimized by the recognition of Chinese entities triples, abstracted from the first extracts the initial triples, and then use neural network to the initial triples, which can identify the entity through our experiment, found that this method not only can well remove the noise of the entity, and can be controlled by neural networks,Allows the result of a triple that can only be parsed as expected.

Paper Details

Date Published: 27 November 2019
PDF: 9 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113211X (27 November 2019); doi: 10.1117/12.2541712
Show Author Affiliations
Yanru Zhong, Guilin Univ. of Electronic Technology (China)
Zhaorong He, Guilin Univ. of Electronic Technology (China)
Leixian Zhao, Guilin Univ. of Electronic Technology (China)
Chaohao Jiang, Guilin Univ. of Electronic Technology (China)
Xiaonan Luo, Guilin Univ. of Electronic Technology (China)


Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray