Research of Chinese word segmentation based on neural network and particle swarm optimization

Author

He, Jia ; Li, Guan-hong

Author_Institution

Sch. of Comput. Sci. & Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu, China

fYear

2010

fDate

17-19 Dec. 2010

Firstpage

56

Lastpage

59

Abstract

For the research of Chinese word segmentation, the BP algorithm model has a lot of defects such as low convergent velocity, easily falling into local minimum, low velocity and efficiency. In this paper, we proposed a new particle swarm neural network algorithm (NPSO-BP), and used it in Chinese word segmentation. The results show that the speed of the segmentation algorithm is obviously faster than the traditional BP neural networks. It has high accuracy and high convergent velocity characteristics.

Keywords

natural language processing; neural nets; particle swarm optimisation; text analysis; Chinese word segmentation; NPSO-BP; particle swarm neural network algorithm; particle swarm optimization; Accuracy; Algorithm design and analysis; Artificial neural networks; Mathematical model; Neurons; Particle swarm optimization; Training; Chinese word segmentation; NPSO-BP algorithm; Neural network; Particle Swarm Optimization;

fLanguage

English

Publisher

ieee

Conference_Titel

Apperceiving Computing and Intelligence Analysis (ICACIA), 2010 International Conference on

Conference_Location

Chengdu

Print_ISBN

978-1-4244-8025-8

Type

conf

DOI

10.1109/ICACIA.2010.5709850

Filename

5709850