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

A transition-based joint model for disease named entity recognition and normalization.

Yinxia Lou1,2, Yue Zhang3, Tao Qian4

  • 1Computer School, Wuhan University, Wuhan, 430072, China.

Bioinformatics (Oxford, England)
|April 4, 2017
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

M$^{3}$3D: A Multimodal, Multilingual and Multitask Dataset for Grounded Document-Level Information Extraction.

IEEE transactions on pattern analysis and machine intelligence·2025
Same author

Report is a mixture of topics: Topic-guided radiology report generation.

Medical image analysis·2025
Same author

Transferring enhanced material knowledge via image quality enhancement and feature distillation for pavement condition identification.

Scientific reports·2025
Same author

Emoji multimodal microblog sentiment analysis based on mutual attention mechanism.

Scientific reports·2024
Same author

TDT-MIL: a framework with a dual-channel spatial positional encoder for weakly-supervised whole slide image classification.

Biomedical optics express·2024
Same author

Generative Biomedical Event Extraction With Constrained Decoding Strategy.

IEEE/ACM transactions on computational biology and bioinformatics·2024
Same journal

Biomedical Concept Recognition with Error-aware Negative-enhanced Ranking Framework.

Bioinformatics (Oxford, England)·2026
Same journal

TEDLH: Domain HMMs for sensitive detection of remote homologues.

Bioinformatics (Oxford, England)·2026
Same journal

PLNFGL: Joint Estimation of Multi-Condition Gene Networks from Single-cell RNA-seq Data.

Bioinformatics (Oxford, England)·2026
Same journal

MCFST: Spatial domain identification method based on multi-view graph convolutional network and graph fusion network.

Bioinformatics (Oxford, England)·2026
Same journal

SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers.

Bioinformatics (Oxford, England)·2026
Same journal

EDEL: Enhancing Dense Retrievers for Curation of Biomedical Knowledge Bases.

Bioinformatics (Oxford, England)·2026
See all related articles

This study introduces a novel joint model for disease named entity recognition and normalization, improving accuracy by integrating these tasks. The new approach outperforms existing pipeline methods in biomedical text analysis.

Area of Science:

  • Biomedical Informatics
  • Natural Language Processing
  • Computational Biology

Background:

  • Accurate identification and normalization of disease entities are crucial for biomedical research.
  • Current pipeline models for disease named entity recognition (DER) and normalization (DEN) suffer from error propagation and limited integration.
  • Existing methods fail to leverage the complementary strengths of DER and DEN.

Purpose of the Study:

  • To develop a novel, integrated model for joint disease named entity recognition and normalization.
  • To overcome the limitations of traditional pipeline approaches in biomedical text analysis.
  • To improve the accuracy and efficiency of extracting disease information from text.

Main Methods:

  • A transition-based model was proposed for joint DER and DEN, framed as an incremental state transition process.

Related Experiment Videos

  • The model learns sequences of transition actions globally, enabling joint structural outputs.
  • Beam search and online structured learning were employed, with learning guiding the search process, allowing for non-local feature utilization.

    • Main Results:

    • The joint framework achieved significantly higher performance compared to pipeline baselines on the BioCreative V CDR and NCBI disease corpora.
    • The proposed method demonstrated favorable comparisons with other state-of-the-art approaches.
    • The joint model effectively addresses error propagation issues inherent in pipeline systems.

    Conclusions:

    • The developed transition-based joint model offers a superior approach for disease named entity recognition and normalization.
    • This integrated method enhances the accuracy of biomedical information extraction.
    • The findings suggest a new direction for developing advanced natural language processing tools in the biomedical domain.