> top > projects > CORD-PICO
CORD-PICO  
in Collections
Description
Automatic annotation of the CORD-19 dataset with PICO categories. The corpus was automatically labeled with an LSTM-CRF model trained on human-annotated PubMed abstracts from https://github.com/bepnye/EBM-NLP. Currently, titles and abstracts only are annotated using Population, Intervention and Outcome labels, as well as more fine-grained labels such as Age, Drug, Mortality and others.

Status Developing
Maintainer ssuster
Author Simon Suster
License Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Documents
CORD-19 26,850
Annotations (69,618)
Download
Not prepared yet for this project.
Contact the manager of this project.
Evaluations Evaluations (0)