This repository contains the Pytorch implementation of Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks.
Download GloVe vectors from here and put it into dataset/ folder
Next Install the required libraries:
- Assume you have installed Pytorch >= 1.5
- 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
- Install PytorchLightning github
- Install from requirements.txt by
pip install -r requirements.txtand runpython -m spacy download en_core_web_sm
python main.py
python main.py --mode test --ckpt_path [your_ckpt_file_path]If you find the code helpful in your research, please cite:
@article{chen2020dialogue,
title={Dialogue relation extraction with document-level heterogeneous graph attention networks},
author={Chen, Hui and Hong, Pengfei and Han, Wei and Majumder, Navonil and Poria, Soujanya},
journal={Cognitive Computation},
year={2022}
}