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

Text structures in medical text processing: empirical evidence and a text understanding prototype

U Hahn1, M Romacker

  • 1Text Knowledge Engineering Lab, Freiburg University, Germany.

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

Glucagon-like peptide-1 receptor agonists for treatment of diabetes and obesity: advantage of oral delivery.

Frontiers in drug delivery·2025
Same author

Practical implementation of the planar and spatial rotator in a complex tissue: the brain.

Journal of microscopy·2018
Same author

[Glaucoma in inpatient care in Germany in 2015].

Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft·2018
Same author

Activating KIR Haplotype Influences Clinical Outcome Following HLA-Matched Sibling Hematopoietic Stem Cell Transplantation.

HLA·2018
Same author

[Employed and self-employed specialists in outpatient ophthalmological care : Comparison with other specialist fields].

Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft·2017
Same author

[Systematic Review of the Application of Complementary and Alternative Medicine and their Potential Therapeutic Benefits in the Treatment of Ophthalmology Patients].

Klinische Monatsblatter fur Augenheilkunde·2016

Recognizing textual structures like anaphora is crucial for accurate medical knowledge bases. Failing to do so leads to invalid representations in natural language understanding systems.

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Natural Language Processing

Background:

  • Medical knowledge bases are essential for healthcare.
  • Natural language understanding (NLU) systems are increasingly used to populate these bases.
  • The accurate representation of medical information is critical for its validity.

Purpose of the Study:

  • To investigate the impact of textual structures on the validity of medical knowledge bases.
  • To analyze the consequences of not recognizing local coherence phenomena in medical texts.
  • To propose a medical text understanding system that addresses these challenges.

Main Methods:

  • Reviewing empirical study results on medical text samples.
  • Examining local coherence phenomena, including anaphora and textual ellipses.

Related Experiment Videos

  • Analyzing representation bias in knowledge bases due to unaddressed textual phenomena.

    • Main Results:

    • Lack of recognition for textual structures leads to referentially incoherent and invalid knowledge base representations.
    • Empirical study highlights the significance of local coherence phenomena (anaphora, ellipses).
    • Identified representation bias in knowledge bases when these phenomena are overlooked.

    Conclusions:

    • Accurate medical knowledge bases require robust NLU systems that account for textual structures.
    • Addressing local coherence phenomena is vital for maintaining the validity of medical information.
    • The proposed system aims to improve the reliability of medical knowledge bases through better text understanding.