MULTI-DOCUMENT SUMMARIZATION Using NEURAL NETWORK

Abstract

Multi-document summarization system is employed to summarize many documents into a brief one with generated new sentences.Several of them are supported word-graph and ILP methodology and much of sentences are unnoticed owing to the significant computation load.To reduce computation and generate decipherable and informative summaries, we tend to propose a completely unique multi-document summarization system using Latent Dirichlet Allocation(LDA) model which is widely used topic modeling technique.LDA model is used to classify text documents to a particular topic.Our approach also use the lexrank to score sentences and summaries of documents to generate informative and higher linguistic quality summaries than existing system.