Skip to content

Towards precise PICO extraction from ab-stracts of randomized controlled trials using a section-specific learning approach

Notifications You must be signed in to change notification settings

BIDS-Xu-Lab/section_specific_annotation_of_PICO

Repository files navigation

This file briefly describes the steps to train/predict PICO entities.
1. Create virtual environment using conda.
$ conda create -n PICO python=3.7
$ conda activate PICO

2. Install PyTorch.
Using Cuda, please choose compatible cuda version with torch (reference: https://pytorch.org/get-started/previous-versions/):
$ conda install pytorch==1.12.0 torchvision==0.13.0 torchaudio==0.12.0 cudatoolkit=11.6 -c pytorch -c conda-forge
Without using Cuda
$ conda install pytorch cpuonly -c pytorch

3. Install transformers.
$ pip install transformers==4.6.0

4. Install seqeval
$ pip install seqeval

5. Install tensorboardX
$ pip install tensorboardX

6. config PICO_ner.py for input data dir, model dir, and output data dir.

7. Run PICO_ner.py to train the model and predict on the test dataset.

About

Towards precise PICO extraction from ab-stracts of randomized controlled trials using a section-specific learning approach

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published