Skip to content

Latest commit

 

History

History
19 lines (13 loc) · 706 Bytes

README.md

File metadata and controls

19 lines (13 loc) · 706 Bytes

Implementations of our paper GSum: A General Framework for Guided Neural Abstractive Summarization.

Code

The bart and bert repos contain code and documentations for BART- and BERT-based models respectively.

The scripts repo contains some helper functions for extracting the guidance signals.

Citation

@inproceedings{dou2021gsum,
  title={GSum: A General Framework for Guided Neural Abstractive Summarization},
  author={Dou, Zi-Yi and Liu, Pengfei and Hayashi, Hiroaki and Jiang, Zhengbao and Neubig, Graham},
  booktitle={Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
  year={2021}
}