PROFER: Predictive, robust finite-state parsing for spoken language

Edward C. Kaiser, Michael Johnston, Peter Heeman

Research output: Chapter in Book/Report/Conference proceedingChapter

14 Citations (Scopus)

Abstract

The natural language processing component of a speech understanding system is commonly a robust, semantic parser, implemented as either a chart-based transition network, or as a generalized left-right (GLR) parser. In contrast, we are developing a robust, semantic parser that is a single, predictive finite-state machine. Our approach is motivated by our belief that such a finite-state parser can ultimately provide an efficient vehicle for tightly integrating higher-level linguistic knowledge into speech recognition. We report on our development of this parser, with an example of its use, and a description of how it compares to both finite-state predictors and chart-based semantic parsers, while combining the elements of both.

Original languageEnglish (US)
Title of host publicationICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherIEEE
Pages629-632
Number of pages4
Volume2
StatePublished - 1999
EventProceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99) - Phoenix, AZ, USA
Duration: Mar 15 1999Mar 19 1999

Other

OtherProceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99)
CityPhoenix, AZ, USA
Period3/15/993/19/99

Fingerprint

semantics
Semantics
charts
natural language processing
Turing machines
linguistics
speech recognition
Finite automata
Speech recognition
Linguistics
vehicles
Processing
predictions

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

Kaiser, E. C., Johnston, M., & Heeman, P. (1999). PROFER: Predictive, robust finite-state parsing for spoken language. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (Vol. 2, pp. 629-632). IEEE.

PROFER : Predictive, robust finite-state parsing for spoken language. / Kaiser, Edward C.; Johnston, Michael; Heeman, Peter.

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2 IEEE, 1999. p. 629-632.

Research output: Chapter in Book/Report/Conference proceedingChapter

Kaiser, EC, Johnston, M & Heeman, P 1999, PROFER: Predictive, robust finite-state parsing for spoken language. in ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. vol. 2, IEEE, pp. 629-632, Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99), Phoenix, AZ, USA, 3/15/99.
Kaiser EC, Johnston M, Heeman P. PROFER: Predictive, robust finite-state parsing for spoken language. In ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2. IEEE. 1999. p. 629-632
Kaiser, Edward C. ; Johnston, Michael ; Heeman, Peter. / PROFER : Predictive, robust finite-state parsing for spoken language. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Vol. 2 IEEE, 1999. pp. 629-632
@inbook{f5bd7ffdcb484ec8980878b387052dc8,
title = "PROFER: Predictive, robust finite-state parsing for spoken language",
abstract = "The natural language processing component of a speech understanding system is commonly a robust, semantic parser, implemented as either a chart-based transition network, or as a generalized left-right (GLR) parser. In contrast, we are developing a robust, semantic parser that is a single, predictive finite-state machine. Our approach is motivated by our belief that such a finite-state parser can ultimately provide an efficient vehicle for tightly integrating higher-level linguistic knowledge into speech recognition. We report on our development of this parser, with an example of its use, and a description of how it compares to both finite-state predictors and chart-based semantic parsers, while combining the elements of both.",
author = "Kaiser, {Edward C.} and Michael Johnston and Peter Heeman",
year = "1999",
language = "English (US)",
volume = "2",
pages = "629--632",
booktitle = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "IEEE",

}

TY - CHAP

T1 - PROFER

T2 - Predictive, robust finite-state parsing for spoken language

AU - Kaiser, Edward C.

AU - Johnston, Michael

AU - Heeman, Peter

PY - 1999

Y1 - 1999

N2 - The natural language processing component of a speech understanding system is commonly a robust, semantic parser, implemented as either a chart-based transition network, or as a generalized left-right (GLR) parser. In contrast, we are developing a robust, semantic parser that is a single, predictive finite-state machine. Our approach is motivated by our belief that such a finite-state parser can ultimately provide an efficient vehicle for tightly integrating higher-level linguistic knowledge into speech recognition. We report on our development of this parser, with an example of its use, and a description of how it compares to both finite-state predictors and chart-based semantic parsers, while combining the elements of both.

AB - The natural language processing component of a speech understanding system is commonly a robust, semantic parser, implemented as either a chart-based transition network, or as a generalized left-right (GLR) parser. In contrast, we are developing a robust, semantic parser that is a single, predictive finite-state machine. Our approach is motivated by our belief that such a finite-state parser can ultimately provide an efficient vehicle for tightly integrating higher-level linguistic knowledge into speech recognition. We report on our development of this parser, with an example of its use, and a description of how it compares to both finite-state predictors and chart-based semantic parsers, while combining the elements of both.

UR - http://www.scopus.com/inward/record.url?scp=0032658202&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032658202&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0032658202

VL - 2

SP - 629

EP - 632

BT - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

PB - IEEE

ER -