A Model for Adaptive Information Retrieval

  • Authors:
  • Fabio Crestani;Cornelis J. Van Rijsbergen

  • Affiliations:
  • Dipartimento di Elettronica e Informatica, Universitá/di Padova, I-35131 Padova, Italy/ E-mail: fabio@dei.unipd.it;Department of Computing Science, University of Glasgow, Glasgow G12 8QQ, Scotland/ E-mail: keith@dcs.gla.ac.uk

  • Venue:
  • Journal of Intelligent Information Systems
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

The paper presents a network model that can be used toproduce conceptual and logical schemas for Information Retrievalapplications. The model has interesting adaptability characteristicsand can be instantiated in various effective ways. The paper alsoreports the results of an experimental investigation into theeffectiveness of implementing associative and adaptive retrieval onthe proposed model by means of Neural Networks. The implementationmakes use of the learning and generalisation capabilities of theBackpropagation learning algorithm to build up and use applicationdomain knowledge in a sub-symbolic form. The knowledge is acquiredfrom examples of queries and relevant documents. Three differentlearning strategies are introduced, their performance is analysed andcompared with the performance of a traditional Information Retrievalsystem.