Analysing Fuzzy Based Approach for Extractive Text Summarization

Abstract

In today’s era of information, there is gigantic amount of data available from various sources. Not only does the enormous volumes pose problems, searching of required information becomes a very difficult task. It is the need of the hour to have smaller but significant representation of large, bulky pieces of information in order to obtain the desired details. Text summarization is the process of condensing text documents into shorter and accurate representation conveying the meaning of the text precisely. It has found applications in numerous fields. In this paper, a process for extractive text summarization using fuzzy logic has been discussed meticulously. It takes various properties into account for identifying the most significant sentences for the formation of summary from a given text. The model proposed in this paper has been tested on BBC News Summary dataset and the results have been compared using the ROUGE measures. The obtained results indicate that the proposed model shows enhanced performance with improved f-measure values.