Earticle

초록

영어

The paper proposes an extraction approach for short Chinese documents topic sentences based on lexical chains and context technology, with which narrative clues of documents are found out first. Multiple lexical chains are constructed subsequently before the extraction of a topic-information-rich one as the keyword sequence of topic sentences. Experimental results demonstrate that this approach covers information of documents to the greater extent, and that it avoids possible repetitive expression that is caused by different keyword sequences in expressing the same topic sentences. Therefore, it achieves an obviously better effect than the statistic approach.

목차

Abstract
 1. Introductions
 2. Extraction of Short Chinese Documents Topics
  2.1. Construction of Lexical Chains
  2.2. Construction Algorithm of Lexical Chains
 3. Analyses of the Algorithm and Experimental Results
  3.1. Analysis of the Algorithm
  3.2. Experiment Results and Analysis
 4. Conclusions
 Acknowledgments
 References

키워드

저자

• WanLi Feng [ School of Computer and Software Engineer, Huaiyin Institute of Technology, HuaiAn, JiangSu, 223003, P. R. China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Multimedia and Ubiquitous Engineering

• 간기

  월간

• pISSN

  1975-0080

• 수록기간

  2008~2016

• 등재여부

  SCOPUS

• 십진분류

  KDC 505 DDC 605