Document Summarization Leveraging Modified LexRank Algorithm

Abstract

In today’s world, documents are composed of complex data and values. So, to tackle this issue, the summarization techniques have come into play. Text summarization basically means to form or generate a short and crisp summary of text in the document, while still kee** the original meaning of the text same. This paper explains about an innovative approach to summarize the text by creating a modified version of the algorithm. This modified algorithm adjusts the threshold value of with the number of lines present in the original text. Since this algorithm prioritize the words, it ranks the sentences from the original text and then selects the most important words from it. Then it creates the summary of the document. By using this methodology, the strain of information overload is eased and enhances the understanding of voluminous text data. By studying the result, it is found that the similarity between the original text and the modified algorithm text is much more similar than the original algorithm.