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 Concept Videos

ER Retrieval Pathway01:45

ER Retrieval Pathway

4.6K
In the secretory pathway, vesicles transport proteins from one cellular compartment to another in forward transport to deliver the protein to its correct location. Occasionally, misfolded proteins and incorrect proteins escape their original compartments, and a retrieval pathway is used to return the escaped proteins to their original compartment.
The ER uses many checkpoints to prevent the entry of incorrectly folded or a resident protein as cargo onto a transport vesicle. These mechanisms...
4.6K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Identifying the Question Similarity of Regulatory Documents in the Pharmaceutical Industry by Using the Recognizing Question Entailment System: Evaluation Study.

JMIR AI·2024
See all related articles

Related Experiment Video

Updated: Jan 4, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

950

Combining Contextualized Embeddings and Prior Knowledge for Clinical Named Entity Recognition: Evaluation Study.

Min Jiang1, Todd Sanger1, Xiong Liu1

  • 1Eli Lilly and Company, Indianapolis, IN, United States.

JMIR Medical Informatics
|November 14, 2019
PubMed
Summary
This summary is machine-generated.

Combining multiple contextualized embeddings and a semantic lexicon significantly improves named entity recognition (NER) in clinical text, even with reduced training data.

Keywords:
contextualized word embeddingdeep learningnamed entity recognitionnatural language processingprior knowledgesemantic embedding

More Related Videos

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

526
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K

Related Experiment Videos

Last Updated: Jan 4, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

950
Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

526
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

2.0K

Area of Science:

  • Clinical Natural Language Processing (NLP)
  • Bioinformatics
  • Computational Linguistics

Background:

  • Named Entity Recognition (NER) is crucial for clinical NLP tasks.
  • Deep learning models, particularly those using contextualized word embeddings, show promise for NER.
  • Few studies explore combining multiple embeddings and prior knowledge for clinical NER.

Purpose of the Study:

  • To enhance clinical NER performance by integrating multiple contextualized word embeddings.
  • To investigate the impact of incorporating prior knowledge, such as semantic lexicons, on NER accuracy.

Main Methods:

  • Developed a deep neural network model for clinical NER.
  • Evaluated the combination of various contextualized embeddings (e.g., ELMo, Flair) with traditional embeddings.
  • Assessed the performance improvement gained by integrating a medical semantic lexicon.

Main Results:

  • The combined embedding approach achieved an F-1 score of 87.30% on a subset of the I2B2 NER dataset.
  • Incorporating a medical lexicon further boosted the F-1 score to 87.44%.
  • The system maintained strong performance (F-1 score of 85.36%) even with 40% reduced training data.

Conclusions:

  • Combining contextualized embeddings offers significant benefits for clinical NER.
  • Semantic lexicons can be effectively utilized to further improve the performance of clinical NER systems.