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

Alternative ways for knowledge collection, indexing and robust language retrieval

R H Baud1, C Lovis, A M Rassinoux

  • 1Division of Medical Informatics, Geneva University Hospital, Switzerland. Robert.Baud@dim.hcuge.ch

Methods of Information in Medicine
|December 29, 1998
PubMed
Summary
This summary is machine-generated.

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

Initial results from the New Horizons exploration of 2014 MU<sub>69</sub>, a small Kuiper Belt object.

Science (New York, N.Y.)·2019
Same author

Spectrally resolved helium absorption from the extended atmosphere of a warm Neptune-mass exoplanet.

Science (New York, N.Y.)·2018
Same author

Clinical Data Reuse or Secondary Use: Current Status and Potential Future Progress.

Yearbook of medical informatics·2017
Same author

Health and Clinical Management.

Yearbook of medical informatics·2016
Same author

A 2'200-bed laboratory: research and education in medical informatics at Geneva University Hospitals.

Yearbook of medical informatics·2016
Same author

DIOGENE 2, a distributed Hospital Information System with an emphasis on ist Medical Information Contenct.

Yearbook of medical informatics·2016

This study defines key knowledge representation entities for Natural Language Processing (NLP), focusing on words, expressions, and concepts. It introduces a method for conceptual indexing and querying medical texts using a Medical Linguistic Knowledge Base (MLKB).

Area of Science:

  • Natural Language Processing (NLP)
  • Knowledge Representation
  • Medical Informatics

Background:

  • Natural Language Processing (NLP) relies on understanding linguistic components like words, expressions, and concepts.
  • Effective knowledge representation is crucial for NLP tasks, especially in specialized domains like medicine.
  • Previous work includes developing a natural language-based patient encoding browser.

Purpose of the Study:

  • To define key entities in knowledge representation for NLP.
  • To explore the granularity of concepts in NLP models.
  • To present a robust method for conceptual indexing and querying medical texts using a Medical Linguistic Knowledge Base (MLKB).

Main Methods:

  • Defining fundamental NLP entities: words, expressions, and concepts.

Related Experiment Videos

  • Analyzing concept granularity within different models.
  • Identifying four categories of linguistic knowledge as building blocks for an MLKB.
  • Developing a conceptual indexing and query method based on prior experience.

    • Main Results:

    • Established definitions for core knowledge representation entities in NLP.
    • Investigated the optimal level of detail (granularity) for concepts.
    • Recognized four essential categories of linguistic knowledge for MLKB construction.
    • Presented a practical method for indexing and querying medical texts conceptually.

    Conclusions:

    • A structured approach to knowledge representation entities enhances NLP capabilities.
    • The proposed method provides effective conceptual indexing and querying for medical texts.
    • The developed MLKB framework supports advanced medical information retrieval.