Multi-document Summarization Using Deep Learning

Due to the advancement of the Internet nowadays, a lot of people are mostly dependent on the Web to get the required information. As data is increasing exponentially, there is a high chance of duplication of data; it is difficult and tedious for the manual reading of all the documents as well as the rejection of the duplicates and extraction of useful information. One of the solutions to this issue is “Text Summarization,” through which a huge volume of data can be read quickly; but it is very hard to summarize documents manually, thus necessitating the use of an automatic tool to perform this task. Abstractive Text Summarization is one such automated technique of producing a short and accurate summary of a document while preserving essential information and comprehensive meaning. In this paper, Abstractive Text Summarization using Deep Learning with Attention Mechanism has been proposed. The designed framework removes duplicate data and generates new sentences by rephrasing them or adding words originally absent in the source text. Experimental results on the dataset, Amazon Fine Food Review, are evaluated by utilizing performance metrics such as Rouge scores.