A Spectral Method for Unsupervised Multi-Document Summarization

Kexiang Wang, Baobao Chang, Zhifang Sui


Abstract
Multi-document summarization (MDS) aims at producing a good-quality summary for several related documents. In this paper, we propose a spectral-based hypothesis, which states that the goodness of summary candidate is closely linked to its so-called spectral impact. Here spectral impact considers the perturbation to the dominant eigenvalue of affinity matrix when dropping the summary candidate from the document cluster. The hypothesis is validated by three theoretical perspectives: semantic scaling, propagation dynamics and matrix perturbation. According to the hypothesis, we formulate the MDS task as the combinatorial optimization of spectral impact and propose an accelerated greedy solution based on a surrogate of spectral impact. The evaluation results on various datasets demonstrate: (1) The performance of the summary candidate is positively correlated with its spectral impact, which accords with our hypothesis; (2) Our spectral-based method has a competitive result as compared to state-of-the-art MDS systems.
Anthology ID:
2020.emnlp-main.32
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
435–445
Language:
URL:
https://aclanthology.org/2020.emnlp-main.32
DOI:
10.18653/v1/2020.emnlp-main.32
Bibkey:
Cite (ACL):
Kexiang Wang, Baobao Chang, and Zhifang Sui. 2020. A Spectral Method for Unsupervised Multi-Document Summarization. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 435–445, Online. Association for Computational Linguistics.
Cite (Informal):
A Spectral Method for Unsupervised Multi-Document Summarization (Wang et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.32.pdf
Video:
 https://slideslive.com/38939222