Combining Graph Degeneracy and Submodularity for Unsupervised Extractive Summarization

Antoine Tixier, Polykarpos Meladianos, Michalis Vazirgiannis


Abstract
We present a fully unsupervised, extractive text summarization system that leverages a submodularity framework introduced by past research. The framework allows summaries to be generated in a greedy way while preserving near-optimal performance guarantees. Our main contribution is the novel coverage reward term of the objective function optimized by the greedy algorithm. This component builds on the graph-of-words representation of text and the k-core decomposition algorithm to assign meaningful scores to words. We evaluate our approach on the AMI and ICSI meeting speech corpora, and on the DUC2001 news corpus. We reach state-of-the-art performance on all datasets. Results indicate that our method is particularly well-suited to the meeting domain.
Anthology ID:
W17-4507
Volume:
Proceedings of the Workshop on New Frontiers in Summarization
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venue:
WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
48–58
Language:
URL:
https://aclanthology.org/W17-4507
DOI:
10.18653/v1/W17-4507
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/W17-4507.pdf
Code
 Tixierae/EMNLP2017_NewSum