Statistical approach based keyword extraction aid dimensionality reduction

Abstract

In the text document analysis process keywords are often represented in bag-of-words or vector space model. This representation is high-dimensional and sparse. Keyword extraction is considered as core technology of all automatic processing for text materials. Keywords represent in condensed from the essential content of a document. In this paper we used keyword extraction techniques for find an index terms that contain most important information and unique identify the documents. We proposed keyword extraction based text summarization techniques helps to reduce dimensionality of the vector space model at initial level. © 2012 Springer-Verlag GmbH Berlin Heidelberg.