An NLP System for Extracting and Representing Knowledge from Abbreviated Text
Deryle W. Lonsdale, Merrill Hutchison, Tim Richards, William Taysom · ScholarsArchive (Brigham Young University) · 2001
This paper presents a new natural language processing (NLP) system called LG-Soar. The system is based at its most fundamental level on the Soar cogni-tive modeling intelligent agent architecture (Newell 1990). The system represents the integration of three major processing com-ponents: (1) regular-expression-based text preprocessing; (2) the Link Grammar parser; and (3) the Soar intelligent agent architec-ture. The result is a robust, versatile text processing engine useful for difficult-to-handle input. Unlike a related Soar-based NLP system, NL-Soar (Lewis 1993), this new system is not specifically designed for cog-nitive modeling of natural language use. The project addresses several interesting