Skip to content
conftrace_
2017 ACL ACL 2017

Oracle Summaries of Compressive Summarization

AbstractThis 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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization and Natural Language Processing
🧭 Keyword Pioneer - rouge score
🐣 Hot Topic Early Bird - text summarization

More from ACL 2017

All ACL 2017 papers →