Skip to content

Prompt Learning is a new paradigm in Natural Language Processing(NLP), which uses pre-trained language models to perform downstream tasks, avoiding fine tuning of a model. This zero-shot learning approach can be applied to healthcare applications, where there is limited availability of data. This projects aims to design prompt methodologies for …

Notifications You must be signed in to change notification settings

PittNAIL/HealthPrompt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

37 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

HealthPrompt

Prompt Learning is a new paradigm in Natural Language Processing(NLP), which uses pre-trained language models to perform downstream tasks, avoiding fine tuning of a model. This zero-shot learning approach can be applied to healthcare applications, where there is limited availability of data. This project aims to design prompt methodologies for downstream applications using PLMs, without the need for model training. This approach can change "Deep Learning" to "Deep Thinking" in Healthcare sector.

Architecture

Development

HealthPrompt is developed by Sonish Sivarajkumar and Dr. Yanshan Wang.

Implementation

HealthPrompt is implemented by Sonish Sivarajkumar.

Citation

Please cite our paper

@article{sivarajkumar2022healthprompt,
  title={HealthPrompt: A Zero-shot Learning Paradigm for Clinical Natural Language Processing},
  author={Sivarajkumar, Sonish and Wang, Yanshan},
  journal={arXiv preprint arXiv:2203.05061},
  year={2022}
}

About

Prompt Learning is a new paradigm in Natural Language Processing(NLP), which uses pre-trained language models to perform downstream tasks, avoiding fine tuning of a model. This zero-shot learning approach can be applied to healthcare applications, where there is limited availability of data. This projects aims to design prompt methodologies for …

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published