The model is implemented using PyTorch. The versions of packages used are shown below.
- numpy==1.18.0
- scikit-learn==0.22.1
- scipy==1.4.1
- torch==1.4.0
- tqdm==4.41.1
- transformers==4.0.0
To set up the dependencies, you can run the following command:
pip install -r requirements.txt
bash scipts/run_large_tacred.sh
bash scripts/run_large_tacrev.sh
bash scripts/run_large_retacred.sh
bash scripts/run_large_semeval.sh