Towards More Effective Text Summarization Based on Textual Association Networks
- 1 December 2008
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 235-240
- https://doi.org/10.1109/skg.2008.17
Abstract
This paper proposes new text summarization approaches based on textual unit association networks. Textual units refer to words, phrases, sentences, or paragraphs. Intuitively, textual units containing much co-occurrence information are semantically more salient in a document. We construct two kinds of textual association networks, namely, word-based association network and sentence-based association network. For the former, we propose anew approach to computing the word weights and sentence weights.For the latter, we develop a new scheme to score each sentence based on its co-occurrence information. Extensive experiments on benchmark data show that our proposed approaches can achieve better summarization performance than the existing methods. Our approaches are unsupervised, independent of languages, and efficient for different text genre.Keywords
This publication has 13 references indexed in Scilit:
- RANDOM WALK TERM WEIGHTING FOR IMPROVED TEXT CLASSIFICATIONInternational Journal of Semantic Computing, 2007
- China's e-science knowledge grid environmentIEEE Intelligent Systems, 2004
- Automatic evaluation of summaries using N-gram co-occurrence statisticsPublished by Association for Computational Linguistics (ACL) ,2003
- Viewpoint: From TeraGrid to knowledge gridCommunications of the ACM, 2001
- A new approach to unsupervised text summarizationPublished by Association for Computing Machinery (ACM) ,2001
- The anatomy of a large-scale hypertextual Web search engineComputer Networks and ISDN Systems, 1998
- Ranking text units according to textual saliency, connectivity and topic aptnessPublished by Association for Computational Linguistics (ACL) ,1998
- Automatic text structuring and summarizationInformation Processing & Management, 1997
- Abstract generation based on rhetorical structure extractionPublished by Association for Computational Linguistics (ACL) ,1994
- New Methods in Automatic ExtractingJournal of the ACM, 1969