Training and evaluation of a spoken language understanding system

Dahl, Deborah A.; Hirschman, Lynette; Norton, Lewis M.; Linebarger, Marcia C.; Magerman, David M.; Nguyen, Minh Duc; Ball, Kelsey

doi:10.3115/116580.128769

Cited by 9 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, although improvements in word accuracy were minimal, application accuracy was greatly improved. This is consistent with previous experiments we have done on speech recognizer output [6]. Additional detail on this experiment can be found in [7].…”

Section: Optical Character Recognitionsupporting

confidence: 91%

Recent improvements and benchmark results for the Paramax ATIS system

Norton

Dahl

Linebarger

1992

Proceedings of the Workshop on Speech and Natural Language - HLT '91

View full text Add to dashboard Cite

This paper describes three relatively domain-independent capabilities recently added to the Paramax spoken language understanding system: non-monotonic reasoning, implicit reference resolution, and database query paraphrase. In addition, we discuss the results of the February 1992 ATIS benchmark tests. We describe a variation on the standard evaluation metric which provides a more tightly controlled measure of progress. Finally, we briefly describe an experiment which we have done in extending the n-best speech/language integration architecture to improving OCR accuracy.

show abstract

Section: Optical Character Recognitionsupporting

confidence: 91%

Recent improvements and benchmark results for the Paramax ATIS system

Norton

Dahl

Linebarger

1992

Proceedings of the Workshop on Speech and Natural Language - HLT '91

View full text Add to dashboard Cite

show abstract

“…Our method for using linguistic context to improve OCR output [5] is based on extending work previously done in Sl)ok(:n language uuderstanding [6,7], where a natural languag,' system is used to constrain tile output of a spee('h recognizer. We have applied linguistic constraints to the OCR using a variation of the N-best interface with th,: natural language processing system, PUNDIT.…”

Section: Recognition Correctionmentioning

confidence: 99%

Integrated text and image understanding for document understanding

Taylor

Dahl

Lipshutz

et al. 1994

Proceedings of the Workshop on Human Language Technology - HLT '94

View full text Add to dashboard Cite

Because of the complexity of documents and the variety of applications which must be supported, document understanding requires the integration of image understanding with text understanding. Our docum(,nt understanding technology is implemented in a system called IDUS (Intelligent Document Undcrstanding System), which creates the data for a text retrieval application and the automatic generation of hyperttrxt li.ks. This paper summarizes the areas of research during IDUS development where we have found the most benelit from the integration of image and text understanding.

show abstract

“…PUNDIT then processed the selected candidate to produce the spoken language system output. The value of N of 16 was selected on the basis of experiments reported in [1], which demonstrated that using larger N's than 10-15 leads to a situation where the chance of getting an F begins to outweigh the possible benefit of additional T's.…”

Section: Class A: Unsays Pundit System Coupled With Mit Summitmentioning

confidence: 99%

Augmented role filling capabilities for semantic interpretation of spoken language

Norton¹,

Linebarger²,

Dahl³

et al. 1991

Proceedings of the Workshop on Speech and Natural Language - HLT '91

View full text Add to dashboard Cite

This paper describes recent work on the Unisys ATIS Spoken Language System, and reports benchmark results on natural language, spoken language, and speech recognition. We describe enhancements to the system's semantic processing for handling non.transparent argument structure and enhancements to the system's pragmatic processing of material in art. swers displayed to the user. We found that the system's score on the natural language benchmark test decreased from ~8~o to 36~ without these enhancements. We also report results for three spoken language systems, Unisys natural language coupled with MIT-Summit speech recognition, Unisys natural language coupled wish MIT-Lincoln Labs speech recognition and Unisys natural language coupled with BBN speech recognition. Speech recognition results are reported on the results of the Unisys natural language selecting a candidate from the MIT-Summit N-best (N=16).

show abstract

Training and evaluation of a spoken language understanding system

Cited by 9 publications

References 17 publications

Recent improvements and benchmark results for the Paramax ATIS system

Recent improvements and benchmark results for the Paramax ATIS system

Integrated text and image understanding for document understanding

Augmented role filling capabilities for semantic interpretation of spoken language

Contact Info

Product

Resources

About