Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level

Chenlong Zhao, Xiwen Zhou, Xiaopeng Xie, Yong Zhang


Abstract
Scientific document summarization has been a challenging task due to the long structure of the input text. The long input hinders the simultaneous effective modeling of both global high-order relations between sentences and local intra-sentence relations which is the most critical step in extractive summarization. However, existing methods mostly focus on one type of relation, neglecting the simultaneous effective modeling of both relations, which can lead to insufficient learning of semantic representations. In this paper, we propose HAESum, a novel approach utilizing graph neural networks to locally and globally model documents based on their hierarchical discourse structure. First, intra-sentence relations are learned using a local heterogeneous graph. Subsequently, a novel hypergraph self-attention layer is introduced to further enhance the characterization of high-order inter-sentence relations. We validate our approach on two benchmark datasets, and the experimental results demonstrate the effectiveness of HAESum and the importance of considering hierarchical structures in modeling long scientific documents.
Anthology ID:
2024.findings-naacl.45
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
714–726
Language:
URL:
https://aclanthology.org/2024.findings-naacl.45
DOI:
10.18653/v1/2024.findings-naacl.45
Bibkey:
Cite (ACL):
Chenlong Zhao, Xiwen Zhou, Xiaopeng Xie, and Yong Zhang. 2024. Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 714–726, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level (Zhao et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.45.pdf