Memory-based parsing

摘要

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.