Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

The roles of language processing in a spoken language interface

L Hirschman1

  • 1Massachusetts Institute of Technology Laboratory for Computer Science, Cambridge 02139, USA.

Proceedings of the National Academy of Sciences of the United States of America
|October 24, 1995
PubMed
Summary

Natural language understanding (NLU) systems offer understanding but limited constraint in speech recognition. Studying interactive systems is key to unlocking discourse context for real-world applications.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Data base design for natural language medical data.

Journal of medical systems·1982
Same author

An experiment in automated health care evaluation from narrative medical records.

Computers and biomedical research, an international journal·1981
Same author

Families at risk for father-daughter incest.

The American journal of psychiatry·1981
Same author

Incest between fathers and daughters.

The Journal of nursing care·1978

Area of Science:

  • Computational Linguistics
  • Artificial Intelligence
  • Human-Computer Interaction

Background:

  • Current natural language understanding (NLU) systems primarily focus on understanding spoken input.
  • Existing NLU systems offer limited constraint in the speech recognition process, often using post-processing methods.
  • The computational expense of current constraint methods restricts their effectiveness.

Purpose of the Study:

  • To review the dual role of language processing in speech recognition and understanding.
  • To explore the potential of discourse context as a significant source of constraint in NLU.
  • To advocate for the study of interactive systems to advance NLU technology.

Main Methods:

  • Overview of a colloquium discussion session on natural language understanding.

Related Experiment Videos

  • Review of existing approaches to integrating language processing in speech recognition.
  • Analysis of the limitations of current unidirectional interfaces and post-processing techniques.

    • Main Results:

    • Language processing has achieved success in understanding but provides limited constraint.
    • Current systems often employ loosely coupled, unidirectional interfaces for NLU.
    • Discourse context offers substantial constraint but remains underexplored.

    Conclusions:

    • Further research into discourse constraint is necessary for more robust NLU systems.
    • Studying interactive systems is crucial for identifying appropriate applications for current NLU technology.
    • Advancing NLU requires moving beyond laboratory settings toward real-world interactive problem-solving contexts.