Abstract

A hybrid natural language understanding (NLU) system which is particularly designed for processing natural language text. Primary functional components of the NLU system include a preprocessor; a word look-up and morphology module which communicates with a lexicon and a learning module; a syntactic parser which interfaces with an augmented transition network (ATN) grammar; a case frame applier, which converts the syntactic structure into canonical, semantic "case frames"; and a discourse analysis component which integrates explicit and implied information in the text into a conceptual structure which represents its meaning. This structure may be passed on to a knowledge based system, data base, to interested analysts or decision makers, etc. Significant feedback points are provided, e.g., the case frame applier may notify the syntactic parser of a semantically incorrect parse, or the syntactic parser may seek a semantic judgment based on a fragmentary parse. This system incorporates a novel semantic analysis approach based largely on case grammar.

Other References

• Loatman, R. B. & McCown, M. G., Information Extraction from Natural Language Messages, Reprint from Proceedings of ESIG--Third Annual Expert Systems in Government Conference, Oct. 19-23, 1987
• Loatman, R. B., A Hybrid Architecture for Natural Language Understanding, Reprint from Proceedings of SPIE--International Society of Optical Engineering, May 18-20, 1987
• R. B. Loatman article, Natural Language Text Understanding, at pp. 2-5 of Jul. 1986, Technology Newsletter (Assignee Internal Publication)
• Undated Brochure of Assignee, "Innovative Solution for AMHS", (author unknown)
• M. Bates, 1987, "The Theory & Practice of Augmented Transition Network Grammers", in L. Bolc (ed.) Natural Language Communication with Computers, New York, Springer
• Winograd, T., 1983, Language as a Cognitive Process, vol. 1: Syntax, Reading, Mass: Addison-Wesley, (Chapter 5, Appendix D), 195-271, 583-599
• Quirk, R., Greenbaum, S., Leech, G., & Svartvik, J., 1985, A Comprehensive Grammer of the English Language, New York: Seminar Press (excerpts from Chapter 10, Appendix I)
• Sager, N., 1981, Natural Language Information Processing: A Computer Grammar of English and Its Applications, Reading, Mass.: Addison-Wesley (excerpts from Appendix I)
• Wilks, V., Haung, X., & Fass, D., 1985, "Syntax, Preference, and Right Attachment", Proceedings of the Ninth IJCAI
• Loatman, R. B., 1988, "Natural Language Text Understanding", Article to be published in assignee Newsletter, (cf. reference AT)
• Dept. of Navy, NOSC, May 21, 1987, Memo Concerning Conference Later Held (at which various NLU Systems were eventually demonstrated)
• Schank, R., 1985, Conceptual Information Processing, New York: North-Holland, (excerpts from Chapter 3)
• Cook, W., 1979, Case Grammer: Development of the Matrix Model, Washington, D.C.: Georgetown University Press, (excerpts)
• Laffal, J., 1973, A Concept Dictionary of English, Essex, Conn.: Gallery Press, (excerpts)
• Marcus, M., 1980, Theory of Syntactic Recognition for Natural Language, Cambridge, Mass.: MIT Press, (excerpts