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

Models of natural language understanding

M Bates1

  • 1BBN Systems and Technologies, Cambridge, MA 02138, USA.

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

This paper reviews natural language (NL) understanding challenges and current solutions. Future NL processing requires better grammars, automatic model derivation, and improved portability for wider application.

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

Listening to and learning from patients: A review of the results from the 2023 national radiotherapy patient experience survey in England.

Radiography (London, England : 1995)·2026
Same author

The experience of Cultural Stress in the School System among Puerto Rican Hurricane Maria migrant families.

Journal of Latina/o psychology·2025
Same author

Amplifying the Patient Voice: A Survey of Practitioners' Use of Patient-reported Outcome Measures Across Radiotherapy Providers in England.

Clinical oncology (Royal College of Radiologists (Great Britain))·2022
Same author

ESR1, PGR, ERBB2, and MKi67 mRNA expression in postmenopausal women with hormone receptor-positive early breast cancer: results from ABCSG Trial 6.

ESMO open·2021
Same author

Multiplex profiling identifies clinically relevant signalling proteins in an isogenic prostate cancer model of radioresistance.

Scientific reports·2019
Same author

Sudden Death: Myocardial Infarction in a Runner With Normal Coronary Arteries.

The Physician and sportsmedicine·2016

Area of Science:

  • Computational Linguistics
  • Natural Language Processing

Background:

  • Fundamental challenges in natural language (NL) understanding include syntax, semantics, pragmatics, and discourse.
  • Current approaches are shifting towards corpus-based methods and measuring system effectiveness.

Purpose of the Study:

  • To survey fundamental problems in NL understanding.
  • To review current and future approaches to solving these problems.
  • To identify key areas for advancement in NL processing technology.

Main Methods:

  • Review of existing literature and research in natural language understanding.
  • Analysis of current trends and developments in NL processing.
  • Identification of critical areas for future research and development.

Main Results:

  • Recent developments emphasize corpus-based work, system evaluation, discourse phenomena, and integrating analytic/stochastic knowledge.
  • Future needs include robust grammars for real language, automated model derivation, self-adapting systems, and speech integration.
  • Portability remains a significant barrier to the widespread application of NL technology.

Conclusions:

  • Advancements in NL understanding require better grammars, automated learning, and system adaptability.
  • Addressing challenges in portability is crucial for practical NL system deployment.
  • Integration with speech processing and tuning for specific requirements are vital for future progress.

Related Experiment Videos