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 name-internal and contextual features to classify biological terms.

Manabu Torii1, Sachin Kamboj, K Vijay-Shanker

  • 1Department of Computer and Information Sciences, University of Delaware, Newark, DE 19716, USA. torii@cis.udel.edu

Journal of Biomedical Informatics
|November 16, 2004
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

Spatiotemporal distribution of air pollutants in UP-NCR, India: a 5-year analysis of pollution trends and meteorological influences.

Environmental monitoring and assessment·2026
Same author

Enhanced Adverse-Event Detection and Drug-Event Relation Extraction from Clinical Notes.

medRxiv : the preprint server for health sciences·2026
Same author

Pretraining effective T5 generative models for clinical and biomedical applications.

PloS one·2026
Same author

Integrating text mining and knowledge graph to enhance biopharmaceutical process optimization.

PloS one·2026
Same author

KSMoFinder-knowledge graph embedding of proteins and motifs for predicting kinases of human phosphosites.

Bioinformatics advances·2025
Same author

KSMoFinder - Knowledge graph embedding of proteins and motifs for predicting kinases of human phosphosites.

bioRxiv : the preprint server for biology·2025
Same journal

Evaluation of temporal preservation in synthetic longitudinal patient data.

Journal of biomedical informatics·2026
Same journal

ARKE: An ontology-driven framework for automated mapping of local radiology procedure terms to the LOINC-RadLex playbook using large language model.

Journal of biomedical informatics·2026
Same journal

A validation-driven training controller for cross-lingual biomedical NER via reinforcement learning-based adaptive loss weighting.

Journal of biomedical informatics·2026
Same journal

ASP-HR: An Adaptive Spatial Perception and Hierarchical Reasoning mechanism for document-level biomedical relation extraction.

Journal of biomedical informatics·2026
Same journal

Beyond Accuracy: Safety-Centered guidelines for the evaluation of LLM-based therapy recommendation systems for chronic multimorbidity patients.

Journal of biomedical informatics·2026
Same journal

DeepEN: A deep reinforcement learning framework for personalized enteral nutrition in critical care.

Journal of biomedical informatics·2026
See all related articles

This study enhances named entity classification in biomedical text by analyzing features within names and contextual phrases. A novel context-based strategy significantly improves classification performance, achieving an 86 f-score on the GENIA corpus.

Area of Science:

  • Biomedical Natural Language Processing
  • Bioinformatics
  • Computational Biology

Background:

  • Named entity recognition (NER) is crucial for extracting information from biomedical texts.
  • Named entity classification (NEC) is a key subtask within NER.
  • Existing methods often focus on limited feature sets for classification.

Purpose of the Study:

  • To investigate and improve named entity classification in biomedical text.
  • To evaluate the effectiveness of different information sources for classification.
  • To introduce and validate a new context-based strategy for enhanced classification.

Main Methods:

  • Utilized features within the named entity itself.
  • Incorporated features from surrounding phrases.

Related Experiment Videos

  • Developed and applied a novel context-of-occurrence strategy.
  • Conducted experiments on the GENIA corpus (Ver. 3.0).

    • Main Results:

    • The new context-based strategy significantly improved classification performance.
    • Analysis showed the effectiveness of both intra-name and contextual features.
    • Achieved an f-score of 86 in 10-fold cross-validation on the GENIA corpus.

    Conclusions:

    • The proposed context-based strategy is effective for biomedical named entity classification.
    • Comprehensive feature utilization enhances classification accuracy.
    • The findings contribute to advancing information extraction from biomedical literature.