Global and Local Hierarchy-aware Contrastive Framework for Hierarchical Implicit Discourse Relation Recognition (ACL 2023)
arXiv preprint: https://arxiv.org/abs/2211.13873
-
Install
PyTorch
by following the instructions from the official website. -
Install
torch_geometric
by following the instructions from the official website. -
Run the following script to install the remaining dependencies,
pip install -r requirements.txt
- Download the PDTB 2.0 dataset, put it under /raw/
- 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:
@article{DBLP:journals/corr/abs-2211-13873,
author = {Yuxin Jiang and
Linhan Zhang and
Wei Wang},
title = {Global and Local Hierarchy-aware Contrastive Framework for Implicit
Discourse Relation Recognition},
journal = {CoRR},
volume = {abs/2211.13873},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2211.13873},
doi = {10.48550/arXiv.2211.13873},
eprinttype = {arXiv},
eprint = {2211.13873},
timestamp = {Tue, 29 Nov 2022 17:41:18 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2211-13873.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}