Automatic text summarization based on multi-agent particle swarm optimization

Text summarization is the objective extraction of some parts of the text, such as sentence and paragraph, as the document abstract. If there are documents with a large amount of information, extractive text summarization would be arisen as an NP-complete problem. To solve these problems, metaheuristic algorithms are used. In this paper, a method based on multi-agent particle swarm optimization approach is proposed to improve the extractive text summarization. In this method, each particle will be upgraded with the status of multi-agent systems. The proposed method is tested on DUC 2002 standard documents and analyzed by ROUGE evaluation software. The experimental results show that this method has better performance than other compared methods.