An IR model based on a sub-tree representation

  • Authors:
  • Mohand Boughanem;Mustapha Baziz

  • Affiliations:
  • IRIT-Université Paul Sabatier, 118 route de Narbonne, 31062 Toulouse, {boughane, baziz}@irit.fr;IRIT-Université Paul Sabatier, 118 route de Narbonne, 31062 Toulouse, {boughane, baziz}@irit.fr

  • Venue:
  • Proceedings of the 2006 conference on Leading the Web in Concurrent Engineering: Next Generation Concurrent Engineering
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper proposes an approach to information retrieval based on the use of a structure (ontology) that is used both for document (resp. query) indexing and query evaluating. The conceptual structure is hierarchical and it encodes the knowledge of the topical domain of the considered documents. It is formally represented as a tree. In this approach, the query evaluation is based on the comparison of minimal sub-trees containing the two sets of nodes corresponding to the concepts expressed in the document and the query respectively. The comparison is based on the computation of a degree of inclusion of the query tree in the document tree. Experiments undertaken on MuchMore benchmark showed the effectiveness of the approach.