Unisys: description of the Unisys system used for MUC-3

ABSTRACT

This paper describes the Unisys MUC-3 text understanding system, a system based upon a three-tiered approach to text processing in which a powerful <u>knowledge-based</u> form of information retrieval plays a central role. This knowledge-based form of information retrieval makes it possible to define an effective level of text analysis that falls somewhere between what is possible with standard keyword-based information retrieval techniques and deep linguistic analysis.

REFERENCES

• 1: Tim Finin, Rich Fritzson, and Dave Matuzsek. Adding forward chaining and truth maintenance to prolog. In Fifth IEEE Conference on Artificial Intelligence Application, pages 123--130, March 1989.
• 2: Tim Finin, Robin McEntire, Carl Weir, and Barry Silk. A three-tiered approach to natural language text retrieval. In Proceedings of the AAAI workshop on Natural Language Text Retrieval, Los Angeles, July 1991.
• 3: L. Hirschman, M. Palmer, J. Dowding, D. Dahl, M. Linebarger, R. Passonneau, F.-M. Lang, C. Ball, and C. Weir. The PUNDIT natural-language processing system. In AI Systems in Government Conf. Computer Society of the IEEE, March 1989.
• 4: Chris D. Paice, Another stemmer, ACM SIGIR Forum, v.24 n.3, p.56-61, Fall 1990 [doi>10.1145/101306.101310]
• 5: Fernando C. N. Pereira and David H. D. Warren. Definite clause grammars for language analysis---a survey of the formalism and a comparison with augmented transition networks. Artificial Intelligence, 13(3):231--278, 1980.
• 6: Bob Pollack. Message format processing language. Manual, Unisys Center for Advanced Information Technology, August 1989. Version 2.1.
• 7: Carl Weir, Tim Finin, Barry Silk, Marcia Linebarger, and Robin McEntire. Knowledge-based strategies for robust text-understanding. The Eighth Annual Intelligence Community AI/Advance Computing Symposium, March 1991.