SDQE: towards automatic semantic query optimization in P2P systems

  • Authors:
  • Xing Zhu;Hualiang Cao;Yong Yu

  • Affiliations:
  • Department of Computer Science and Engineering, Shanghai Jiao Tong Univeristy, Shanghai, China;Department of Computer Science and Engineering, Shanghai Jiao Tong Univeristy, Shanghai, China;Department of Computer Science and Engineering, Shanghai Jiao Tong Univeristy, Shanghai, China

  • Venue:
  • Information Processing and Management: an International Journal - Special issue: Formal methods for information retrieval
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Conventional information retrieval technology (i.e. VSM) faces many difficulties when being implemented in complex P2P systems for the lack of global statistic information (e.g. IDF) and central services. In this paper, we suggest a novel query optimization scheme (Semantic Dual Query Expansion, SDQE) that makes full use of the context information supplied by the local document collection. Latent Semantic Indexing (LSI) is used to explore the local context information. By comparing the different local context information hidden in different document collections, it is possible to solve the synonymy-polysemy problem in VSM. The experiments prove that our scheme is effective to improve the retrieval performance in P2P systems without knowing the global statistic information.