MAMHOA: a multi-agent meta-heuristic optimization algorithm with an approach for document summarization issues

Abstract

Today, given the increasing volume of information and the difficulty of using them for specific applications such as email, websites, news, etc., the use of automated information summarization algorithms has become more popular than traditional algorithms. Taking advantage of computer algorithms, these algorithms produce a summary of information while retaining its original meaning. However, given its semantic and structural properties as well as the variable comparative parameters of information, the summarization process is considered as an NP-hard problem. Therefore, to solve these problems it is better to use meta-heuristic algorithms, which are generally inspired by the behavior of nature. These meta-heuristic algorithms help to better solve the hard problems through producing optimum solutions. In this paper, we propose an optimization algorithm named multi-agent meta-heuristic optimization algorithm (MAMHOA) for extractive text summarization. MAMHOA is a combination of biogeography-based optimization (BBO) algorithm and multi-agent systems concepts to generate an optimum summary. Several computational tests are used to evaluate the effectiveness and efficiency of the proposed algorithm, which is compared to other algorithms provided in the literature. MAMHOA and other algorithms are tested on DUC2002 datasets and attained solutions are analyzed using ROUGE metrics. From the results obtained, it can be seen that the proposed algorithm is more effective and efficient than those mentioned in the literature i.e. Baseline and state-of-the-art methods for different ROUGE metrics.