Multi-Document Text Summarization Using Deep Belief Network

Abstract

Recently, there is a lot of information available on the Internet, which makes it difficult for users to find what they're looking for. Extractive text summarization methods are designed to reduce the amount of text in a document collection by focusing on the most important information and reducing the redundant information.  Summarizing documents should not affect the main ideas and the meaning of the original text. This paper proposes a new automatic, generic, and extractive multi-document summarizing model aiming at producing a sufficiently informative summary. The idea of the proposed model is based on extracting nine different features from each sentence in the document collection. The extracted features are introduced as input to the Deep Belief Network (DBN) for the classification purpose as either important or unimportant sentences. Only, the important sentences pass to the next phase to construct a graph. The PageRank algorithm is used to assign scores to the graph sentences. The sentences with high scores were selected to create a summary document. The performance of the proposed model was evaluated using the DUC-2004 (Task2) dataset using ROUGE more. The experimental results demonstrate that our proposed model is more effective than the baseline method and some state-of-the-art methods, Where ROUGE-1 reached 0.4032 and ROUGE-2 to 0.1021.