Text-Mining Research Group

Text Summarization: An Old Challenge and New Approaches

One of the most relevant today’s problems called “information overloading” has increased the necessity of more sophisticated and powerful information compression methods - summarizers. This chapter firstly introduces taxonomy of summarization methods, an overview of their principles from classical ones, over corpus based, to knowledge rich approaches. We consider various aspects which can affect their categorization. A special attention is devoted to application of recent information reduction methods, based on algebraic transformations. Our own LSA (Latent Semantic Analysis) based approach is included too. The next part is devoted to evaluation measures for assessing quality of a summary. The taxonomy of evaluation measures is presented and their features are discussed. Further, we introduce experiences with the development of our web searching and summarization system. Finally, some new ideas and a conception for the future of this field are mentioned.

Keywords: Text summarization

Year: 2009

Download:  Full text 

Josef Steinberger

E-mail: jstein@kiv.zcu.cz

Josef is an associated professor at the Department of computer science and engineering at the University of West Bohemia in Pilsen, Czech Republic. He is interested in media monitoring and analysis, mainly automatic text summarisation, sentiment analysis and coreference resolution.

Karel Ježek

Phone:  +420 377632475
E-mail: jezek_ka@kiv.zcu.cz
WWW: https://cs.wikipedia.org/wiki/Karel_Je%C5%BEek_(informatik)

Karel is the former group coordinator and a supervisor of PhD students working at research projects of this Group.

Automatic Text Summarisation
Authors:	Josef Steinberger, Karel Ježek, Michal Campr, Jiří Hynek
Desc.:	Automatic text summarisation using various text mining methods, mainly Latent Semantic Analysis (LSA).