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

DTranNER: biomedical named entity recognition with deep learning-based label-label transition model.

S K Hong1, Jae-Gil Lee2,3

  • 1Graduate School of Knowledge Service Engineering, KAIST, 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, South Korea.

BMC Bioinformatics
|February 13, 2020
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 journal

Model-based quantification of protein-protein interaction aberrations for exploring dysregulated signalling pathways through pathway maps and gene expression levels.

BMC bioinformatics·2026
Same journal

Research on multi-trait genome association study method based on Shannon information entropy.

BMC bioinformatics·2026
Same journal

A multi-view feature fusion framework with interpretable graph convolution for predicting microbe-drug associations.

BMC bioinformatics·2026
Same journal

Covariance decomposition for distance based species tree estimation.

BMC bioinformatics·2026
Same journal

SNPio: a Python interface for population genomic data processing.

BMC bioinformatics·2026
Same journal

SpaHNR: a spatial domain identification method via sparse attention-based hierarchical node representation and multi-view contrastive learning.

BMC bioinformatics·2026

This study introduces DTranNER, a novel framework that enhances biomedical named-entity recognition (BioNER) by dynamically modeling label transitions. DTranNER improves accuracy by using deep learning to adaptively capture contextual relationships between labels in biomedical texts.

Area of Science:

  • Computational biology
  • Bioinformatics
  • Natural Language Processing

Background:

  • Biomedical Named-Entity Recognition (BioNER) is crucial for information extraction from biomedical literature.
  • Traditional Conditional Random Field (CRF) models treat BioNER as a sequence labeling problem, but static label transitions limit performance.
  • Deep learning models combined with CRF have improved BioNER, yet struggle to dynamically adapt label transitions to context.

Purpose of the Study:

  • To introduce DTranNER, a novel CRF-based framework that incorporates a deep learning-based label-label transition model for BioNER.
  • To address the limitations of static transition models in capturing contextual information for accurate entity segmentation.

Main Methods:

  • DTranNER utilizes two distinct deep learning networks: a Unary-Network for individual label prediction and a Pairwise-Network for modeling label-label transitions.
Keywords:
BioinformaticsData miningNamed entity recognitionNeural network

Related Experiment Videos

  • The Pairwise-Network dynamically explores contextual relations between adjacent labels based on input sentence context.

    • Main Results:

    • DTranNER achieved state-of-the-art F1-scores on multiple benchmark BioNER corpora, including BC2GM (84.56%), BC4CHEMD (91.99%), chemical NER (94.16%), and BC5CDR disease NER (87.22%).
    • The framework demonstrated superior performance compared to existing state-of-the-art methods across various biomedical entity recognition tasks.
    • A near-best F1-score of 88.62% was achieved on the NCBI-Disease corpus.

    Conclusions:

    • The integration of a deep learning-based dynamic label-label transition model significantly enhances BioNER performance over static models.
    • DTranNER adaptively captures contextual label relationships, offering a fine-grained approach to improving entity recognition.
    • This framework is expected to advance biomedical literature mining and related research areas.