@inproceedings{zhang-etal-2023-contrastive-hierarchical,
    title = "Contrastive Hierarchical Discourse Graph for Scientific Document Summarization",
    author = "Zhang, Haopeng  and
      Liu, Xiao  and
      Zhang, Jiawei",
    editor = "Strube, Michael  and
      Braud, Chloe  and
      Hardmeier, Christian  and
      Li, Junyi Jessy  and
      Loaiciga, Sharid  and
      Zeldes, Amir",
    booktitle = "Proceedings of the 4th Workshop on Computational Approaches to Discourse (CODI 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.codi-1.4/",
    doi = "10.18653/v1/2023.codi-1.4",
    pages = "37--47",
    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."
}