Affinity-Preserving Random Walk for Multi-Document Summarization

Kexiang Wang, Tianyu Liu, Zhifang Sui, Baobao Chang


Abstract
Multi-document summarization provides users with a short text that summarizes the information in a set of related documents. This paper introduces affinity-preserving random walk to the summarization task, which preserves the affinity relations of sentences by an absorbing random walk model. Meanwhile, we put forward adjustable affinity-preserving random walk to enforce the diversity constraint of summarization in the random walk process. The ROUGE evaluations on DUC 2003 topic-focused summarization task and DUC 2004 generic summarization task show the good performance of our method, which has the best ROUGE-2 recall among the graph-based ranking methods.
Anthology ID:
D17-1020
Volume:
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Editors:
Martha Palmer, Rebecca Hwa, Sebastian Riedel
Venue:
EMNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
210–220
Language:
URL:
https://aclanthology.org/D17-1020
DOI:
10.18653/v1/D17-1020
Bibkey:
Cite (ACL):
Kexiang Wang, Tianyu Liu, Zhifang Sui, and Baobao Chang. 2017. Affinity-Preserving Random Walk for Multi-Document Summarization. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 210–220, Copenhagen, Denmark. Association for Computational Linguistics.
Cite (Informal):
Affinity-Preserving Random Walk for Multi-Document Summarization (Wang et al., EMNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/D17-1020.pdf
Video:
 https://aclanthology.org/D17-1020.mp4