A Method for Multi-text Summarization Based on Multi-Objective Optimization use Imperialist Competitive Algorithm

In this research, we discuss the methods that have been proposed so far to solve automatic summarization, in which both single-text and multi-text are summarized with emphasis on experimental methods and text extraction techniques. In multi-text summarization, retrieving redundant information that is readable and coherent and contains maximum information from the original text and minimum redundancy has made research in this field very important. An extraction approach based on several methods for identifying sentence similarities and a meta-heuristic optimization algorithm that has been modified and optimized for faster convergence is presented. In this algorithm, changes are made based on density detection through the probability distribution function to avoid being placed in local optimization and try to search more extensively for the response space. The experimental results obtained from the implementation of the algorithm show that the efficiency on criteria such as ROUGE and the accuracy of the proposed method is effectively increased.

A Method for Multi-text Summarization Based on Multi-Objective Optimization use Imperialist Competitive Algorithm Keywords:

Automatic Summarization , Optimization , ICA Algorithm , Single-text , Multi-text