DocumentCode :
2920758
Title :
Application of Chinese Word Segmentation Based on Linguistic Environment Analysis in Text Information Filtering System
Author :
Yi, Zhi-an ; Lv, Jia
Author_Institution :
Coll. of Comput. & Inf. Technol., Daqing Pet. Inst., Daqing
fYear :
2009
fDate :
20-22 Feb. 2009
Firstpage :
467
Lastpage :
470
Abstract :
This paper provides Chinese word segmentation based on language analysis problem in text information filtering system. The improved Chinese word segmentation is made of a bigram segmentation and a segmentation correction, new words recognition and disambiguation through the bigram segmentation, check the accuracy of segmentation results using the segmentation correction from the perspective of syntax. It has been proved by experiments that the segmentation not only strengthen the system´s language analysis ability, but also improve the accuracy of text information filtering system when the improved Chinese word segmentation was applied to the text analysis module.
Keywords :
information filtering; natural language processing; text analysis; word processing; Chinese word segmentation; bigram segmentation; language analysis problem; linguistic environment analysis; segmentation correction; syntax; text information filtering system; words recognition; Computer applications; Educational institutions; Information analysis; Information filtering; Information science; Information technology; Internet; Natural languages; Petroleum; Text analysis; Chinese word segmentation; Information filtration; disambiguation; segmentation correction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electronic Computer Technology, 2009 International Conference on
Conference_Location :
Macau
Print_ISBN :
978-0-7695-3559-3
Type :
conf
DOI :
10.1109/ICECT.2009.89
Filename :
4796006
Link To Document :
بازگشت