Education, Science, Technology, Innovation and Life
Open Access
Sign In

A Survey of Research on Deep Learning Entity Relationship Extraction

Download as PDF

DOI: 10.23977/nlpsr.2019.11001 | Downloads: 24 | Views: 1668

Author(s)

Wang Peng 1

Affiliation(s)

1 School of Economics and Management, Dalian University, No.10, Xuefu Avenue, Economic & Technical Development Zone, Dalian, Liaoning, The People's Republic of China(PRC)

Corresponding Author

Wang Peng

ABSTRACT

Entity relationship extraction is the core task and important link in the fields of information extraction, natural language understanding, information retrieval, etc. It can extract the semantic relationship between entity pairs from text. In recent years, the application of deep learning in joint learning and remote supervision The relationship extraction task has obtained rich research results. At present, the deep learning-based entity relationship extraction technology has gradually surpassed the traditional feature-based and kernel-based methods in feature extraction depth and model accuracy. And the two areas of remote supervision, the system summarizes the research progress of Chinese and foreign scholars' deep relationship-based entity relationship extraction in recent years, and discusses and prospects the future research directions.

KEYWORDS

Entity relationship extraction, Deep learning, Joint learning, Remote supervision, Generating confrontation network

CITE THIS PAPER

Wang Peng, A Survey of Research on Deep Learning Entity Relationship Extraction. Natural Language Processing and Speech Recognition (2019) 1: 1-5. DOI: http://dx.doi.org/10.23977/nlpsr.2019.11001.

REFERENCES

[1] Golshan PN,. (1995) A study of recent contributions on information extraction, New Technology of Library and Information Service ,8, 18−23
[2] Gan LX. (2016) Chinese entity relationship extraction based on syntactic and semantic features: IEEE Press,  8, 69−73.
[3] Ratnaweera A. (2004) Self-organizing hierarchical particle swarm optimizer with time-varying acceleration
[4] coefficients. IEEE Transactions on Evolutionary Computation, 6, 712-731.

Downloads: 24
Visits: 1668

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.