ABSTRACT
In this paper, we describe the Template Matcher, a system built at SRI to provide robust natural-language interpretation in the Air Travel Information System (ATIS) domain. The system appears to be robust to both speech recognition errors and unanticipated or difficult locutions used by speakers. We explain the motivation for the Template Matcher, describe in general terms how it works in comparison with similar systems, and examine its performance. We discuss some limitations of this approach, and sketch a plan for integrating the Template Matcher with an analytic parser, which we believe will combine the advantages of both.
- Moore, R. C., and Dowding, J., Efficient Bottom-Up Parsing, Proceedings, Fourth DARPA Workshop on Speech and Natural Language, February 1991. Google ScholarDigital Library
- Schank, R. C. and Yale A. I. Project, SAM---A Story Understander, Research Report 43, Department of Computer Science, Yale University, 1975.Google Scholar
- Ward, W., Understanding Spontaneous Speech, Proceedings, DARPA Speech and Natural Language Workshop, February 1989. Google ScholarDigital Library
- Ward, W., The CMU Air Travel Information Service: Understanding Spontaneous Speech, Proceedings, DARPA Speech and Natural Language Workshop, June 1990. Google ScholarDigital Library
- Rau, L. F., and Jacobs, P. S., Integrating Top-Down and Bottom-Up Strategies in a Text Processing System, Proceedings, Second Conference on Applied Natural Language Processing, Austin, Texas, 1988. Google ScholarDigital Library
- Riesbeck, C., and Schank, R. C., Comprehension by Computer: Expectation-Based Analysis of Sentences in Context, Research Report 78, Department of Computer Science, Yale University, 1976.Google Scholar
- Carbonell, J. G. and Hayes, P. J., Recovery Strategies for Parsing Extragrammatical Language, Technical Report CMU-CS-84--107, Carnegie-Mellon University Computer Science Technical Report, 1984.Google Scholar
Comments