Topic-Guided Abstractive Multi-Document Summarization

Peng Cui, Le Hu


Abstract
A critical point of multi-document summarization (MDS) is to learn the relations among various documents. In this paper, we propose a novel abstractive MDS model, in which we represent multiple documents as a heterogeneous graph, taking semantic nodes of different granularities into account, and then apply a graph-to-sequence framework to generate summaries. Moreover, we employ a neural topic model to jointly discover latent topics that can act as cross-document semantic units to bridge different documents and provide global information to guide the summary generation. Since topic extraction can be viewed as a special type of summarization that “summarizes” texts into a more abstract format, i.e., a topic distribution, we adopt a multi-task learning strategy to jointly train the topic and summarization module, allowing the promotion of each other. Experimental results on the Multi-News dataset demonstrate that our model outperforms previous state-of-the-art MDS models on both Rouge scores and human evaluation, meanwhile learns high-quality topics.
Anthology ID:
2021.findings-emnlp.126
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
1463–1472
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.126
DOI:
10.18653/v1/2021.findings-emnlp.126
Bibkey:
Cite (ACL):
Peng Cui and Le Hu. 2021. Topic-Guided Abstractive Multi-Document Summarization. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1463–1472, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Topic-Guided Abstractive Multi-Document Summarization (Cui & Hu, Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.126.pdf
Data
Multi-News