arXiv preprint: https://arxiv.org/abs/2211.13873

1. Install PyTorch by following the instructions from the official website.

2. Install torch_geometric by following the instructions from the official website.

3. Run the following script to install the remaining dependencies,

pip install -r requirements.txt

1. Download the PDTB 2.0 dataset, put it under /raw/
2. Run the following script for data preprocessing,

python3 preprocess.py

(P.S. PDTB 3.0 can be downloaded from https://catalog.ldc.upenn.edu/LDC2019T05. You can easily modify preprocess.py and adapt it to PDTB 3.0.)

Run the following script for training, evaludating, and testing,

python3 run.py

（Our code can be easily run on a single NVIDIA GeForce RTX 3090)

If you find this work helpful, please cite our paper by:

@inproceedings{jiang-etal-2023-global,
    title = "Global and Local Hierarchy-aware Contrastive Framework for Implicit Discourse Relation Recognition",
    author = "Jiang, Yuxin  and
      Zhang, Linhan  and
      Wang, Wei",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.findings-acl.510",
    pages = "8048--8064",
}