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

Enhancing HMM-based biomedical named entity recognition by studying special phenomena.

Jie Zhang1, Dan Shen, Guodong Zhou

  • 1Institute for Infocomm Research, 21 Heng Mui Keng Terrace, Singapore 119613, Singapore. zhangjie@i2r.a-star.edu.sg

Journal of Biomedical Informatics
|November 16, 2004
PubMed
Summary

This study enhances biomedical named entity recognition using a Hidden Markov Model (HMM) with novel features. The improved system achieves state-of-the-art performance, particularly in recognizing abbreviations and cascaded entities.

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

Integrative profiling of oral fungal communities across <i>Mycobacterium Tuberculosis</i> burden groups in Xpert-positive patients.

Annals of medicine·2026
Same author

Deletion of <i>steD</i> gene and <i>yejAE</i> operons in LPS-deficient <i>Salmonella</i> elicits strong t cell immunity and complete protection against homologous serotypes.

Frontiers in microbiology·2026
Same author

<i>Salmonella</i>-derived OMVs as a vaccine platform for <i>Riemerella anatipestifer</i> outer membrane proteins to prevent infection in ducks.

Applied and environmental microbiology·2026
Same author

Report of a case of renal hilum Castleman disease complicated with Paget's disease of the breast.

Frontiers in medicine·2026
Same author

Engineered OMVs of Salmonella displaying PlpE antigen provide effective protection against Pasteurella multocida infection in mice.

Vaccine·2026
Same author

Pathogen spectrum of pulmonary infections in kidney transplant recipients and the diagnostic value of mNGS: a sputum and BALF study based on clinical decision-making.

Frontiers in cellular and infection microbiology·2026

Area of Science:

  • Biomedical Natural Language Processing
  • Computational Biology
  • Bioinformatics

Background:

  • Named entity recognition (NER) is crucial for extracting information from biomedical texts.
  • Existing NER systems often struggle with the complexity and nuances of biomedical terminology.
  • The need for improved accuracy in identifying biomedical entities like genes, proteins, and diseases is critical.

Purpose of the Study:

  • To enhance a Hidden Markov Model (HMM)-based named entity recognizer specifically for the biomedical domain.
  • To develop effective methods for recognizing biomedical abbreviations and handling cascaded named entity recognition phenomena.
  • To improve the overall performance and accuracy of biomedical NER systems.

Main Methods:

  • Analysis of biomedical named entity characteristics.

Related Experiment Videos

  • Integration of a rich feature set: orthographic, morphological, part-of-speech, and semantic trigger features.
  • Implementation of a Hidden Markov Model (HMM) with back-off modeling.
  • Development of novel methods for biomedical abbreviation recognition and cascaded NER.

    • Main Results:

    • The proposed system achieved F-measures of 66.5 and 62.5 on the GENIA V3.02 and V1.1 datasets, respectively.
    • Outperformed the previous best published system by 8.1 F-measure on the same experimental settings.
    • Demonstrated effective handling of biomedical abbreviations and cascaded named entity recognition.

    Conclusions:

    • The developed rich feature set significantly improves biomedical NER.
    • The proposed methods for abbreviation and cascaded NER are effective and novel.
    • This system represents a significant advancement in biomedical named entity recognition, being the first to address cascaded phenomena.