Content-based peer-to-peer network overlay for full-text federated search

  • Authors:
  • Jie Lu;Jamie Callan

  • Affiliations:
  • Carnegie Mellon University, Pittsburgh, PA;Carnegie Mellon University, Pittsburgh, PA

  • Venue:
  • Large Scale Semantic Access to Content (Text, Image, Video, and Sound)
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

Peer-to-peer network overlays have mostly been designed to support search over document names, identifiers, or keywords from a small or controlled vocabulary. In this paper we propose a content-based P2P network overlay for full-text federated search over heterogeneous, open-domain contents. Local algorithms are developed to dynamically construct a network overlay with content-based locality and content-based small-world properties. Experimental results using P2P testbeds of real documents demonstrate the effectiveness of our approach.