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

Subword segmentation--leveling out morphological variations for medical document retrieval.

U Hahn1, M Honeck, M Piotrowski

  • 1Text Knowledge Engineering Lab, Freiburg University.

Proceedings. AMIA Symposium
|February 5, 2002
PubMed
Summary

This study introduces subword segmentation for medical terms, improving information retrieval. This approach enhances search accuracy by breaking down complex words, outperforming traditional methods.

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

Elevated in-stream CO<sub>2</sub> concentration stimulates net-N<sub>2</sub>O production from global fluvial ecosystems.

Water research·2025
Same author

Insight into the electronic structure of the centrosymmetric skyrmion magnet GdRu<sub>2</sub>Si<sub>2</sub>.

Nanoscale advances·2023
Same author

Disentangling the Impact of Point Defect Density and Carrier Localization-Enhanced Auger Recombination on Efficiency Droop in (In,Ga)N/GaN Quantum Wells.

ACS photonics·2023
Same author

Insight into the Temperature-Dependent Canting of 4f Magnetic Moments from 4f Photoemission.

The journal of physical chemistry letters·2023
Same author

GPCR kinase knockout cells reveal the impact of individual GRKs on arrestin binding and GPCR regulation.

Nature communications·2022
Same author

Efficacy of five 'sporicidal' surface disinfectants against Clostridioides difficile spores in suspension tests and 4-field tests.

The Journal of hospital infection·2022

Area of Science:

  • Medical Informatics
  • Computational Linguistics
  • Natural Language Processing

Background:

  • Medical sublanguages contain complex word structures challenging traditional search.
  • Morphological processes like derivation and composition hinder accurate term matching.

Purpose of the Study:

  • To propose and evaluate a subword segmentation approach for medical terms.
  • To improve information retrieval accuracy for morphologically complex medical vocabulary.

Main Methods:

  • Segmenting morphologically complex medical word forms into meaningful subwords.
  • Applying a matching procedure to both segmented query and document terms.
  • Comparing subword-based indexing and retrieval against conventional string matching.

Related Experiment Videos

Main Results:

  • Subword segmentation effectively addresses challenges posed by medical term morphology.
  • Empirical data demonstrates significantly improved performance of subword-based retrieval.
  • The proposed method eliminates issues from morphologically altered word forms.

Conclusions:

  • Subword-based indexing and retrieval offer a superior alternative to string matching for medical texts.
  • This approach enhances the precision and recall of medical information retrieval systems.
  • Medical term segmentation is crucial for effective natural language processing in healthcare.