The code and data preparation is based on this repo.
- WikiHow.
- PubMedQA. The dataset split for the question-driven summarization can be found via the following repo: https://github.com/dengyang17/hscm.
If the data or code is used in your research, please star this repo and cite our paper as follows:
@inproceedings{DBLP:conf/emnlp/DengZL20,
author = {Yang Deng and
Wenxuan Zhang and
Wai Lam},
title = {Multi-hop Inference for Question-driven Summarization},
booktitle = {Proceedings of the 2020 Conference on Empirical Methods in Natural
Language Processing, {EMNLP} 2020, Online, November 16-20, 2020},
pages = {6734--6744},
year = {2020},
url = {https://doi.org/10.18653/v1/2020.emnlp-main.547},
}