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

Corpus-based identification and refinement of semantic classes

A Nazarenko1, P Zweigenbaum, J Bouaud

  • 1Laboratoire d'Informatique de Paris-Nord, Université Paris 13.

Proceedings : a Conference of the American Medical Informatics Association. AMIA Fall Symposium
|January 1, 1997
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

Pragmatic Considerations on Clinical Decision Support from the 2019 Literature.

Yearbook of medical informatics·2020
Same author

Contributions from the 2017 Literature on Clinical Decision Support.

Yearbook of medical informatics·2018
Same author

Contributions from the 2016 Literature on Clinical Decision Support.

Yearbook of medical informatics·2017
Same author

Making Sense of Big Textual Data for Health Care: Findings from the Section on Clinical Natural Language Processing.

Yearbook of medical informatics·2017
Same author

An artificial metalloenzyme with the kinetics of native enzymes.

Science (New York, N.Y.)·2016
Same author

Computerized Clinical Decision Support: Contributions from 2015.

Yearbook of medical informatics·2016

This study shows that using ZELLIG, a corpus analysis tool, can build and refine semantic categorization for medical language processing. It helps identify domain-specific terms and improve clinical sub-language understanding.

Area of Science:

  • Natural Language Processing
  • Medical Informatics
  • Computational Linguistics

Background:

  • Medical Language Processing (MLP) requires detailed semantic lexica for specialized domains.
  • Existing NLP tools may not fully capture the nuances of clinical sub-language.
  • Developing fine-grained semantic categorizations is crucial for accurate medical text analysis.

Purpose of the Study:

  • To evaluate the effectiveness of robust natural language processing tools in building and refining semantic categorization within a specific domain.
  • To test the hypothesis that corpus analysis tools can aid in creating domain-specific semantic lexica.
  • To assess the utility of the ZELLIG corpus analysis tool for medical language.

Main Methods:

  • Utilized the ZELLIG corpus analysis tool on a representative domain-specific corpus.

Related Experiment Videos

  • Applied clustering techniques to analyze the corpus and identify semantic relationships.
  • Compared the resulting clusters with existing domain models like SNOMED nomenclature.

    • Main Results:

    • The initial clusters generated by ZELLIG aligned with established domain models (e.g., SNOMED nomenclature).
    • The analysis successfully identified coarse-grained semantic categories relevant to the medical domain.
    • The tool effectively isolated unique lexical items specific to clinical sub-language.
    • ZELLIG demonstrated utility in categorizing previously unclassified terms.

    Conclusions:

    • Robust NLP tools, specifically ZELLIG, are effective in building and refining semantic categorizations for medical domains.
    • Corpus analysis aids in understanding both general domain models and specific clinical language idiosyncrasies.
    • ZELLIG facilitates the creation of fine-grained semantic lexica, enhancing medical language processing capabilities.