English

Contrastive Hierarchical Discourse Graph for Scientific Document Summarization

Computation and Language 2023-06-02 v1

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.

Keywords

Cite

@article{arxiv.2306.00177,
  title  = {Contrastive Hierarchical Discourse Graph for Scientific Document Summarization},
  author = {Haopeng Zhang and Xiao Liu and Jiawei Zhang},
  journal= {arXiv preprint arXiv:2306.00177},
  year   = {2023}
}

Comments

CODI at ACL 2023

R2 v1 2026-06-28T10:52:37.309Z