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

A general method for sifting linguistic knowledge from structured terminologies.

N Grabar1, P Zweigenbaum

  • 1DIAM-Service d'Informatique Médicale, DSI, Assistance Publique-Paris Hospitals & Département de Biomathématiques, Université Paris 6, Paris, France. ngr@biomath.jussieu.fr

Proceedings. AMIA Symposium
|November 18, 2000
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

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

Clinical Natural Language Processing in 2015: Leveraging the Variety of Texts of Clinical Interest.

Yearbook of medical informatics·2016
Same author

Clinical Natural Language Processing in 2014: Foundational Methods Supporting Efficient Healthcare.

Yearbook of medical informatics·2015
Same author

Interchanging lexical information for a multilingual dictionary.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2006
Same author

VUMeF: extending the French involvement in the UMLS Metathesaurus.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2004
Same author

Looking for French-English translations in comparable medical corpora.

Proceedings. AMIA Symposium·2002

This study introduces a novel method to learn word morphology from medical terminologies, enhancing medical language processing and information retrieval with high precision and coverage.

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Natural Language Processing

Background:

  • Morphological knowledge is crucial for medical language processing, information retrieval, and developing medical terminologies or ontologies.
  • Existing medical terminologies contain rich semantic relations (synonymy, hierarchy, transversal) that can be leveraged.

Purpose of the Study:

  • To develop a method for learning morphological word associations from structured medical terminologies.
  • To demonstrate the method's independence from a priori linguistic knowledge and its applicability to various structured terminologies.

Main Methods:

  • The approach extracts morphological associations by analyzing semantic relations within existing medical terminologies.
  • No prior linguistic expertise is required, allowing flexibility across different terminologies and relations.

Related Experiment Videos

Main Results:

  • The method achieved high precision (>90%) and good coverage (>88%) when tested on SNOMED and ICD in French and English.
  • For English words with stems longer than 3 characters, recall reached 98.8% for inflection and 94.7% for derivation.

Conclusions:

  • The proposed method effectively identifies reliable morphological relations from medical terminologies.
  • This approach offers a valuable tool for enhancing medical language processing, information retrieval, and ontology development.