Advertisement

The Research of Chinese Q&A System Based on Similarity Algorithm

  • Liu Zhen
  • Xiao Wenxian
  • Wan Wenlong
  • Yulan Li
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 107)

Abstract

On the basis of the research on the theories of the Chinese question answering system, in-depth analysis on the calculation methods of the current statement similarity has been done; the advantages and disadvantages of the calculation methods of the various statements similarity and its application have been studied; a new method of statements similarity calculation is put forward, On this basis, a Chinese question answering system based on a set of frequent questions was achieved. The results show that: the system is better than the current more popular VSM method in the match of the statement similarity.

Keywords

The question answering system Models Questions recognition Questions matching Threshold VSM 

References

  1. 1.
    Sujian L (2002) Research of relevancy between sentences based on semantic computation [J]. Comput Eng Appl 38(7):75–76Google Scholar
  2. 2.
    Li J, Cao X ,Yu F (2008) A word semantic automatic classification system based on word similarity computation [J]. Comput Simul 25(08):295–299Google Scholar
  3. 3.
    Wu Q, Xiong H (2010) Method for sentence similarity computation by integrating multi-features [J]. Comput Syst Appl (11):110 –114Google Scholar
  4. 4.
    Liu J, Zou P, Zhang P, Qi F (2010) Research on an improved algorithm of concept semantic similarity based on ontology [J]. J Wuhan Univ Technol 20:112–117Google Scholar
  5. 5.
    Liu Q, Gu X (2010) Study on HowNet-based word similarity algorithm [J]. J Chin Inf Process 06:31–36Google Scholar
  6. 6.
    Li S (2002) Research of relevancy between sentences based on semantic computation [J]. Comput Eng Appl 38(7):75–76Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2012

Authors and Affiliations

  1. 1.Henan Institute of Science and TechnologyHenan XinxiangChina

Personalised recommendations