Modeling Endorsement for Multi-Document Abstractive Summarization

Logan Lebanoff, Bingqing Wang, Zhe Feng, Fei Liu


Abstract
A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently reiterated in a set of documents related to a particular topic, resulting in an endorsement effect that increases information salience. In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization. Our method generates a synopsis from each document, which serves as an endorser to identify salient content from other documents. Strongly endorsed text segments are used to enrich a neural encoder-decoder model to consolidate them into an abstractive summary. The method has a great potential to learn from fewer examples to identify salient content, which alleviates the need for costly retraining when the set of documents is dynamically adjusted. Through extensive experiments on benchmark multi-document summarization datasets, we demonstrate the effectiveness of our proposed method over strong published baselines. Finally, we shed light on future research directions and discuss broader challenges of this task using a case study.
Anthology ID:
2021.newsum-1.13
Volume:
Proceedings of the Third Workshop on New Frontiers in Summarization
Month:
November
Year:
2021
Address:
Online and in Dominican Republic
Venue:
newsum
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
119–130
Language:
URL:
https://aclanthology.org/2021.newsum-1.13
DOI:
10.18653/v1/2021.newsum-1.13
Bibkey:
Cite (ACL):
Logan Lebanoff, Bingqing Wang, Zhe Feng, and Fei Liu. 2021. Modeling Endorsement for Multi-Document Abstractive Summarization. In Proceedings of the Third Workshop on New Frontiers in Summarization, pages 119–130, Online and in Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Modeling Endorsement for Multi-Document Abstractive Summarization (Lebanoff et al., newsum 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.newsum-1.13.pdf
Video:
 https://aclanthology.org/2021.newsum-1.13.mp4
Code
 ucfnlp/endorser-summ
Data
WCEP