AN APPROACH FOR TEXT SUMMARIZATION USING DEEP LEARNING ALGORITHM | Science Publications

Journal of Computer Science

K. Duraiswamy¹  G. PadmaPriya¹ 

关键词: Multi-Document;    Summary;    Redundancy;    RBM;    DUC 2002 Dataset (Document Understanding Conferences);   

DOI  :  10.3844/jcssp.2014.1.9

学科分类：计算机科学（综合）

来源: Science Publications

【 摘 要 】

Now days many research is going on for text summarization. Because of increasing information in the internet, these kind of research are gaining more and more attention among the researchers. Extractive text summarization generates a brief summary by extracting proper set of sentences from a document or multiple documents by deep learning. The whole concept is to reduce or minimize the important information present in the documents. The procedure is manipulated by Restricted Boltzmann Machine (RBM) algorithm for better efficiency by removing redundant sentences. The restricted Boltzmann machine is a graphical model for binary random variables. It consist of three layers input, hidden and output layer. The input data uniformly distributed in the hidden layer for operation. The experimentation is carried out and the summary is generated for three different document set from different knowledge domain. The f-measure value is the identifier to the performance of the proposed text summarization method. The top responses of the three different knowledge domain in accordance with the f-measure are 0.85, 1.42 and 1.97 respectively for the three document set.

【 授权许可】

Unknown