login

Memory-based parsing

Artificial IntelligencePublished 1 November 1983
Michael Lebowitz
Citations79
SJR quartileQ1
SJR score1.84
SNIP3.30

TL;DR

This paper describes an experiment in extending the parsing methods used by the Integrated Partial Parser, a computer system designed to read and generalize from large numbers of news stories.

Abstract

Robust text understanding systems can be developed by focusing on the application of memory-based parsing techniques. This paper describes an experiment in extending these techniques as far as possible. Described here are the parsing methods used by the Integrated Partial Parser (IPP), a computer system designed to read and generalize from large numbers of news stories. These methods include top-down, «generic, predictions generated from high-level memory structures, and simple, procedural bottom-up heuristics to handle language-specific problems. A detailed example is presented.

Keywords

Computer Science