Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization

Hanqi Jin, Tianming Wang, Xiaojun Wan


Abstract
In this paper, we propose a multi-granularity interaction network for extractive and abstractive multi-document summarization, which jointly learn semantic representations for words, sentences, and documents. The word representations are used to generate an abstractive summary while the sentence representations are used to produce an extractive summary. We employ attention mechanisms to interact between different granularity of semantic representations, which helps to capture multi-granularity key information and improves the performance of both abstractive and extractive summarization. Experiment results show that our proposed model substantially outperforms all strong baseline methods and achieves the best results on the Multi-News dataset.
Anthology ID:
2020.acl-main.556
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Editors:
Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6244–6254
Language:
URL:
https://aclanthology.org/2020.acl-main.556
DOI:
10.18653/v1/2020.acl-main.556
Bibkey:
Cite (ACL):
Hanqi Jin, Tianming Wang, and Xiaojun Wan. 2020. Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6244–6254, Online. Association for Computational Linguistics.
Cite (Informal):
Multi-Granularity Interaction Network for Extractive and Abstractive Multi-Document Summarization (Jin et al., ACL 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.556.pdf
Video:
 http://slideslive.com/38929014