Active memory for text information retrieval

  • Authors:
  • Y. H. Ng;S. P.V. Barros

  • Affiliations:
  • Department of Computing, Imperial College, University of London, LONDON SW7 2BZ;Department of Computer Science, Queen Mary College, University of London, LONDON E1 4NS

  • Venue:
  • SIGIR '88 Proceedings of the 11th annual international ACM SIGIR conference on Research and development in information retrieval
  • Year:
  • 1988

Quantified Score

Hi-index 0.00

Visualization

Abstract

A Symbolic Associative Processor (SAP), capable of supporting parallel Keyword Match and Record Match functions, is proposed to select and streamline textual data for information retrieval. Consequently, high volume text data could be analysed on-the-fly before being channelled to CPU, and thus, cushion the impact of Von Neumann bottleneck commonly experienced in applications requiring high I/O bandwidth. This paper identifies some of the system requirements to support text information retrieval using SAP with the aid of simplified examples.