RESEARCHER: An Overview

Described in this paper is a computer system, RESEARCHER, beine: develoDed at Columbia that reads natural languagk text-in th(? form of patent abstracts and creates. a permanent long-term memory based on concepts generaliz+ from these texts, forming an intelligent mformatlon s stem. This pa er is intended to give an overview of RESEARCHER & e will describe briefly the four main areas dealt ’with in the desi n % of RESEARCHER: 1) knowledge representation w ere a canonical scheme for representing physical objects has been developed, generalization 2) memory-based text processing, 3) and generalization-based organization that treats conce part of understanding, a t formation as an E? ?g% an question answering. 4) generalization-based

Authors

• Michael Lebowitz

Keywords

No keywords are indexed for this paper.