Skip to content

spaCy NER trained on MeasEval data with microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract base

Notifications You must be signed in to change notification settings

meghanabhange/MeasNER

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MeasNER : Bio NER for Counts and Measurements

Built with spaCy

Disclaimer : Work in progress, doesn't give the best accuracy yet.

image

Trained on MeasEval 2021 SemEval data which focuses on Counts and Measurements entities in clinical texts. (Can be extended to other medical entities as well)

Using PubMedBERT-base-uncased-abstract-fulltext as a backbone so can capture token level information corresponding to medical texts better.

Trained using spaCy-v3 and can be used directly as a package.

Installation

pip install https://github.com/meghanabhange/MeasNER/releases/download/0.1/en_measner-0.1.1.tar.gz

About

spaCy NER trained on MeasEval data with microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract base

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages