Contrastive Hierarchical Discourse Graph for Scientific Document Summarization
This work addresses scientific paper summarization for researchers and practitioners, offering an incremental improvement through hierarchical graph modeling.
The paper tackled the challenge of summarizing scientific papers by proposing CHANGES, a contrastive hierarchical graph neural network for extractive summarization, which achieved effectiveness on PubMed and arXiv datasets by capturing hierarchical structure information.
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.