Abstract
The extended structural context has made scientific paper summarization a challenging task. This paper proposes CHANGES, a contrastive hierarchical graph neural network for extractive scientific paper summarization. CHANGES represents a scientific paper with a hierarchical discourse graph and learns effective sentence representations with dedicated designed hierarchical graph information aggregation. We also propose a graph contrastive learning module to learn global theme-aware sentence representations. Extensive experiments on the PubMed and arXiv benchmark datasets prove the effectiveness of CHANGES and the importance of capturing hierarchical structure information in modeling scientific papers.- Anthology ID:
- 2023.codi-1.4
- Volume:
- Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Michael Strube, Chloe Braud, Christian Hardmeier, Junyi Jessy Li, Sharid Loaiciga, Amir Zeldes
- Venue:
- CODI
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 37–47
- Language:
- URL:
- https://aclanthology.org/2023.codi-1.4
- DOI:
- 10.18653/v1/2023.codi-1.4
- Cite (ACL):
- Haopeng Zhang, Xiao Liu, and Jiawei Zhang. 2023. Contrastive Hierarchical Discourse Graph for Scientific Document Summarization. In Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023), pages 37–47, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Contrastive Hierarchical Discourse Graph for Scientific Document Summarization (Zhang et al., CODI 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2023.codi-1.4.pdf