Oracle Summaries of Compressive Summarization

Tsutomu Hirao, Masaaki Nishino, Masaaki Nagata


Abstract
This paper derives an Integer Linear Programming (ILP) formulation to obtain an oracle summary of the compressive summarization paradigm in terms of ROUGE. The oracle summary is essential to reveal the upper bound performance of the paradigm. Experimental results on the DUC dataset showed that ROUGE scores of compressive oracles are significantly higher than those of extractive oracles and state-of-the-art summarization systems. These results reveal that compressive summarization is a promising paradigm and encourage us to continue with the research to produce informative summaries.
Anthology ID:
P17-2043
Volume:
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2017
Address:
Vancouver, Canada
Editors:
Regina Barzilay, Min-Yen Kan
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
275–280
Language:
URL:
https://aclanthology.org/P17-2043
DOI:
10.18653/v1/P17-2043
Bibkey:
Cite (ACL):
Tsutomu Hirao, Masaaki Nishino, and Masaaki Nagata. 2017. Oracle Summaries of Compressive Summarization. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 275–280, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Oracle Summaries of Compressive Summarization (Hirao et al., ACL 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/landing_page/P17-2043.pdf