[BibTeX] [RIS]
Beyond Centrality and Structural Features: Learning Information Importance for Text Summarization
Type of publication: Inproceedings
Citation: ZopfLozaFuernkranz2016CPSum
Booktitle: Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning
Year: 2016
Month: August
Pages: 84-94
Publisher: Association for Computational Linguistics
Location: Berlin, Germany
URL: http://www.aclweb.org/anthology/K16-1009
Abstract: Most automatic text summarization systems proposed to date rely on centrality and structural features as indicators for information importance. In this paper, we argue that these features cannot reliably detect important information in heterogeneous document collections. Instead, we propose CPSum, a summarizer that learns the importance of information objects from a background source. Our hypothesis is tested on a multi-document corpus where we remove centrality and structural features. CPSum proves to be able to perform well in this challenging scenario whereas reference systems fail.
Authors Zopf, Markus
Loza Mencía, Eneldo
Fürnkranz, Johannes