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

Adding a medical lexicon to an English Parser.

Peter Szolovits1

  • 1MIT Laboratory for Computer Science, Cambridge, MA, USA.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|January 20, 2004
PubMed
Summary

We developed a new method to transfer vocabulary between lexicons, enhancing the Link Grammar Parser with extensive medical terms from the National Library of Medicine

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

Toward responsible AI governance: Balancing multi-stakeholder perspectives on AI in healthcare.

International journal of medical informatics·2025
Same author

Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study.

The Lancet. Digital health·2023
Same author

Using machine learning to develop smart reflex testing protocols.

Journal of the American Medical Informatics Association : JAMIA·2023
Same author

An open natural language processing (NLP) framework for EHR-based clinical research: a case demonstration using the National COVID Cohort Collaborative (N3C).

Journal of the American Medical Informatics Association : JAMIA·2023
Same author

Using Machine Learning to Develop Smart Reflex Testing Protocols.

ArXiv·2023
Same author

Clinical Artificial Intelligence: Design Principles and Fallacies.

Clinics in laboratory medicine·2023

Area of Science:

  • Computational Linguistics
  • Medical Informatics
  • Natural Language Processing

Background:

  • Lexicons are crucial for natural language processing (NLP) parsers.
  • Existing parsers may lack specialized domain vocabularies, limiting their application.
  • The Link Grammar Parser requires comprehensive lexical data for accurate syntactic analysis.

Purpose of the Study:

  • To present a heuristic method for mapping lexical information between different lexicons.
  • To augment the Link Grammar Parser's lexicon with a large medical vocabulary.
  • To demonstrate the practical utility of this mapping technique.

Main Methods:

  • Developed a heuristic approach for transferring syntactic information.
  • Applied the method to integrate the National Library of Medicine's Specialist lexicon.
  • Addressed technical challenges in lexicon augmentation.
  • Utilized a corpus of emergency department notes for evaluation.

Main Results:

  • Successfully mapped and integrated a substantial medical vocabulary into the Link Grammar Parser.
  • Demonstrated the feasibility and effectiveness of the heuristic mapping method.
  • Showcased the enhanced parser's capability on real-world medical text.

Conclusions:

  • The heuristic mapping method is effective for enriching NLP lexicons with specialized domain knowledge.
  • Augmenting parsers with large medical vocabularies improves their performance on clinical notes.
  • This approach facilitates the application of advanced NLP techniques in medical informatics.

Related Experiment Videos