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

Using automatically learnt verb selectional preferences for classification of biomedical terms.

Irena Spasić1, Sophia Ananiadou

  • 1Department of Chemistry, UMIST, Faraday Building, P.O. Box 88, Sackville Street, Manchester M60 1QD, UK. i.spasic@umist.ac.uk

Journal of Biomedical Informatics
|November 16, 2004
PubMed
Summary

This study introduces a novel term classification method using verb selectional patterns (VSPs) learned from biomedical text. This approach enhances the accuracy of classifying new biomedical terms.

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

Enhancing the quality and trustworthiness of large language model-generated summaries of clinical oncology literature.

JAMIA open·2026
Same author

Assessing the Feasibility of Using Parents' Social Media Conversations to Inform Burn First Aid Interventions: Mixed Methods Study.

JMIR formative research·2024
Same author

Supporting the working life exposome: Annotating occupational exposure for enhanced literature search.

PloS one·2024
Same author

Word sense disambiguation of acronyms in clinical narratives.

Frontiers in digital health·2024
Same author

Fine-tuning coreference resolution for different styles of clinical narratives.

Journal of biomedical informatics·2023
Same author

Knowledge-enhanced Graph Topic Transformer for Explainable Biomedical Text Summarization.

IEEE journal of biomedical and health informatics·2023

Area of Science:

  • Biomedical Informatics
  • Computational Linguistics
  • Natural Language Processing

Background:

  • Automated term classification is crucial for organizing biomedical knowledge.
  • Existing methods may lack the specificity required for complex biomedical terminology.

Purpose of the Study:

  • To develop and evaluate an automated term classification approach using verb selectional patterns (VSPs).
  • To leverage domain-specific ontologies and corpora for enhanced term recognition and classification.

Main Methods:

  • Verb selectional patterns (VSPs) were automatically learned from a biomedical corpus and ontology.
  • Term recognition involved dictionary lookups and the C/NC-value method.
  • Two machine learning approaches, iterative generalization and genetic algorithms, were employed for VSP learning.

Related Experiment Videos

  • A nearest-neighbor approach, combining contextual, lexical, and syntactic features, was used for term classification.

    • Main Results:

    • Successfully acquired verb selectional patterns (VSPs) for domain-specific verbs.
    • Demonstrated the utility of VSPs in constraining the search space for term classification.
    • Achieved effective classification of newly recognized terms based on their co-occurrence with domain-specific verbs.

    Conclusions:

    • Verb selectional patterns offer a robust framework for automated term classification in the biomedical domain.
    • The proposed method effectively utilizes linguistic patterns and machine learning for improved biomedical term categorization.