To read this content please select one of the options below:

Contemporary Cybernetics

Kybernetes

ISSN: 0368-492X

Article publication date: 1 February 1989

39

Abstract

Whilst at the Department of Computer Science at Columbia University, US, Michael Lebowitz, currently at the Analytical Proprietary Trading Unit of Morgan Stanley and Company, New York, researched into a variety of areas in natural language processing and machine learning. In particular his UNIMEM learning program has been applied to a wide range of domains including census data, software evaluation and congressional voting records. In a recent research contribution, “The Use of Memory in Text Processing”, Communications of the ACM, Vol. 31 No. 12, 1988, pp. 1483–1505, he describes how RESEARCHER, a program that reads, remembers and generalises from patent abstracts, makes use of its automatically generated memory to assist low‐level text processing. This, he says, involves disambiguation that could be accomplished in no other way.

Citation

(1989), "Contemporary Cybernetics", Kybernetes, Vol. 18 No. 2, pp. 6-22. https://doi.org/10.1108/eb005810

Publisher

:

MCB UP Ltd

Copyright © 1989, MCB UP Limited

Related articles