Abstract
Redundancy is frequent in natural language. Words, phrases, clauses and even complete sentences can sometimes be removed without essentially changing the content of a text. Text summarization, a technique to generate concise summaries, capitalizes on this feature of language. Experience with traditional text summarization, using a statistical analysis of syntactic relations (Sparck Jones, 1993), (Endres-Niggemeyer, 1998), (Hovy, 2005), (Mani, 2001) shows its limitations. In our view, those limitations are related to the use of formal ontologies and the lack of a uniform method of knowledge representation. Formal ontologies do not respect the properties of cognitive activity and cannot support a meaningful summarization of concepts. As traditional knowledge representation can be complex and text summarization may require an analysis of the input from different perspectives, the use of uniform representation, enabling a combination of knowledge from different domains in a single representation, by means of structural coordination, can be beneficial for reasons of efficiency.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Sarbo, J.J., Farkas, J.I., van Breemen, A.J.J. (2011). Text summarization. In: Knowledge in Formation. Cognitive Technologies. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17089-8_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-17089-8_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17088-1
Online ISBN: 978-3-642-17089-8
eBook Packages: Computer ScienceComputer Science (R0)