Title :
A novel Chinese text topic extraction method based on LDA
Author_Institution :
School of Information Technology, Jiangxi University of Finance and Economics, Nanchang, China
Abstract :
This paper proposed a novel Chinese text topic extraction method based on Latent Dirichlet Allocation model. This method was practiced in CCL, an authoritative Chinese corpus, to extract topics for its nine categories. Our results exhibit LDA has better performance in precision rate than any other comparable techniques.
Keywords :
"Filtering","Feature extraction","Data models","Resource management","Semantics","Mathematical model","Probabilistic logic"
Conference_Titel :
Computer Science and Network Technology (ICCSNT), 2015 4th International Conference on
DOI :
10.1109/ICCSNT.2015.7490707
