Stochastically-Based Semantic Analysis / Edition 1

by Wolfgang Minker, Alex Waibel, Joseph Mariani

Overview

Shastically-Based Semantic Analysis investigates the problem of automatic natural language understanding in a spoken language dialog system. The focus is on the design of a shastic parser and its evaluation with respect to a conventional rule-based method.
Shastically-Based Semantic Analysis will be of most interest to researchers in artificial intelligence, especially those in natural language processing, computational linguistics, and speech recognition. It will also appeal to practicing engineers who work in the area of interactive speech systems.

Product Details

ISBN-13:	9780792385714
Publisher:	Springer US
Publication date:	08/31/1999
Series:	The Springer International Series in Engineering and Computer Science , #514
Edition description:	1999
Pages:	221
Product dimensions:	6.10(w) x 9.25(h) x 0.02(d)

Table of Contents

1. Introduction.- 2. Research Framework.- 3. Applications and Corpora.- 4. Portability of a Rule-Based Case Frame Parser.- 5. Shastically-Based Case Frame Parser.- 6. Portability of the Shastic Parser.- 7. Summary of Results.- 8. Conclusion.- Appendices.- A- Rule-based Language Porting.- B- Case Values in French and English.- C- System Query Language for L’ATIS.- D- Test Subsets.- E- Commonly-used Abbreviations.- F- Utterance References.- References.

Editorial Reviews

‘Altogether the book is well worth reading. The research reported in this book is very interesting, and the authors managed to almost find the right level of detail in their descriptions, enabling the reader to understand how a system works without losing the overall picture.'
Natural Language Engineering, 7:1 (2001)

From the Publisher

An American and two French scientists investigate the problem of automatic natural language understanding for spoken language systems, and propose a parsing method that is sufficiently general and flexible to be ported easily to different applications, domains, and human languages. As examples, they apply their stochastic method to the American Air Travel Service Kiosk and the French Multimodal-Multimedia Automated Service Kiosk, both of which use interactions between people and machines to deal with retrieving information for air and train travel, and to the English Spontaneous Speech Task, which concerns interaction between two people who are negotiating to schedule a meeting. Annotation c. Book News, Inc., Portland, OR (booknews.com)

Booknews