Clement25 / dialog-HGAT

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

dialog-HGAT

Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks

Setup

Download GloVe vectors from here and put it into dataset/ folder

Next Install the required libraries:

1. Assume you have installed Pytorch >= 1.5
2. Install dgl library according to your cuda version using the commands below

pip install --pre dgl-cu100     # For CUDA 10.0 Build
pip install --pre dgl-cu101     # For CUDA 10.1 Build
pip install --pre dgl-cu102     # For CUDA 10.2 Build

3. Install PytorchLightning github
4. Install from requirements.txt by pip install -r requirements.txt and run python -m spacy download en_core_web_sm

Run code

Training

python main.py

Testing

python main.py --mode test --ckpt_path [your_ckpt_file_path]

Paper Link

https://arxiv.org/pdf/2009.05092.pdf