Title :
Chinese Keyword Extraction Based on Word Platform
Author :
Jiao, Hui ; Liu, Qian ; Jia, Hui-bo
Author_Institution :
Tsinghua Univ., Beijing
Abstract :
At present researches on Chinese keyword extraction mainly focus on automatic segmentation which is a pretreatment problem. This paper presents a kind of Chinese encoding method based on word platform, and establishes a new Chinese document format in computer. This method makes word the smallest information unit. Chinese keyword extraction does not rely on segmentation by this new method. Thereby the efficiency and quality could be improved. Statistical analysis is adopted to conduct the experiment of keyword extraction based on word platform, and experimental results are satisfying.
Keywords :
document handling; natural languages; statistical analysis; Chinese encoding method; Chinese keyword extraction; automatic segmentation; statistical analysis; Data mining; Encoding; Frequency; Instruments; Laboratories; Machine assisted indexing; Natural language processing; Statistical analysis; Statistics; Web pages;
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2007. FSKD 2007. Fourth International Conference on
Conference_Location :
Haikou
Print_ISBN :
978-0-7695-2874-8
DOI :
10.1109/FSKD.2007.215