A novel approach for text summarization using optimal combination of sentence scoring methods

In this paper, a novel multi-document summarization scheme based on metaheuristic optimization is introduced that generates a summary by extracting salient and relevant sentences from a collection of documents. The proposed work generates optimal combinations of sentence scoring methods and their respective optimal weights to extract the sentences with the help of a metaheuristic approach known as teaching-learning-based optimization. In addition, the proposed scheme is compared to two summarization methods that use different metaheuristic approaches. The experimental results show the efficacy of the proposed summarization scheme.