作者: Hsinchun Chen , Thian-Huat Ong
DOI:
关键词:
摘要: There has been renewed research interest in using the statistical approach to extraction of key phrases from Chinese documents because existing approaches do not allow online frequency updates after have extracted. This consequently results inaccurate, partial extraction. In this paper, we present an updateable PAT-tree approach. our experiment, compared with that Lee-Feng Chien showed improvement recall 0.19 0.43 and precision 0.52 0.70. paper also reviews requirements for a data structure facilitates implementation any key-phrase extraction, including PATtree, PAT-array suffix array semi-infinite strings.