Multi Graph Neural Network for Extractive Long Document Summarization

Xuan-Dung Doan, Le-Minh Nguyen, Khac-Hoai Nam Bui


Abstract
Heterogeneous Graph Neural Networks (HeterGNN) have been recently introduced as an emergent approach for extracting document summarization (EDS) by exploiting the cross-relations between words and sentences. However, applying HeterGNN for long documents is still an open research issue. One of the main majors is the lacking of inter-sentence connections. In this regard, this paper exploits how to apply HeterGNN for long documents by building a graph on sentence-level nodes (homogeneous graph) and combine with HeterGNN for capturing the semantic information in terms of both inter and intra-sentence connections. Experiments on two benchmark datasets of long documents such as PubMed and ArXiv show that our method is able to achieve state-of-the-art results in this research field.
Anthology ID:
2022.coling-1.512
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5870–5875
Language:
URL:
https://aclanthology.org/2022.coling-1.512
DOI:
Bibkey:
Cite (ACL):
Xuan-Dung Doan, Le-Minh Nguyen, and Khac-Hoai Nam Bui. 2022. Multi Graph Neural Network for Extractive Long Document Summarization. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5870–5875, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Multi Graph Neural Network for Extractive Long Document Summarization (Doan et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.512.pdf
Code
 dungdx34/mtgnn-sum