A Fast and Compact Method for Document Summarization on Mobile Devices Using Non-Negative Matrix Factorization
With a fast paced economy, organization need to make a decision as fast as possible, access to large text documents or other information sources is important during decision making. Unfortunately, there are many shortcomings of the handheld devices, such as limited resolution and narrow bandwidth. In order to overcome the shortcomings, this paper proposes fast and compact approaches that can summarize documents on mobile devices efficiently. The presented method introduces unsupervised schemes using Non-negative Matrix Factorization (NMF) that can determine the sentence precedence without morphological and syntax analysis.