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

Semi-supervised disentangled framework for transferable named entity recognition.

Zhifeng Hao1, Di Lv2, Zijian Li2

  • 1School of Computer Science, Guangdong University of Technology, Guangzhou, China; School of Mathematics and Big Data, Foshan University, Guangzhou, China.

Neural Networks : the Official Journal of the International Neural Network Society
|December 31, 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 author

Scalable and controllable synthesis of metallic nanoparticles via synthetic microbiomes.

Biotechnology advances·2026
Same author

A critical review of the oxygen paradox in mainstream anaerobic ammonium oxidation: dissolved oxygen as a cross-scale driver from microbial adaptation to process stability.

Bioresource technology·2026
Same author

Water-MAS: A multi-agent LLM framework with instruction-data decoupling for smart water management.

Water research·2026
Same author

Pulmonary nodule growth prediction with anisotropic reaction-diffusion.

Computer methods and programs in biomedicine·2026
Same author

Machine learning-based study of breath sounds in children with asthma in remission and cough variant asthma.

BMC medical informatics and decision making·2026
Same author

Neurovascular decoupling is associated with altered glymphatic function as assessed by the DTI-ALPS index in patients on dialysis.

Brain imaging and behavior·2026
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a novel semi-supervised framework for transferable Named Entity Recognition (NER). The model effectively disentangles domain-specific and domain-invariant information, improving cross-domain and cross-lingual NER performance.

Area of Science:

  • Natural Language Processing
  • Machine Learning
  • Artificial Intelligence

Background:

  • Named Entity Recognition (NER) is crucial for information extraction but requires extensive labeled data.
  • Current cross-domain NER models struggle with extracting domain-invariant and integrating domain-specific information.

Purpose of the Study:

  • To develop a semi-supervised framework for transferable NER that addresses challenges in cross-domain adaptation.
  • To improve the generalizability and performance of NER models across different domains and languages.

Main Methods:

  • A semi-supervised framework that disentangles domain-invariant and domain-specific latent variables.
  • Utilizes a domain predictor to integrate domain-specific information.
  • Employs three mutual information regularization terms for variable disentanglement.
Keywords:
DisentanglementNamed entity recognitionSemi-supervised learningTransfer learning

Related Experiment Videos

Main Results:

  • Achieved state-of-the-art performance on cross-domain NER benchmark datasets.
  • Demonstrated effective extraction of domain-invariant and integration of domain-specific information.
  • Showcased strong results in cross-lingual NER tasks.

Conclusions:

  • The proposed framework offers a robust solution for transferable NER by effectively managing domain-specific and invariant information.
  • This approach significantly enhances NER model performance in cross-domain and cross-lingual settings.
  • The method reduces the reliance on large labeled datasets through its semi-supervised and domain adaptation capabilities.