Automatic Persian text summarizer using simulated annealing and genetic algorithm

Automatic text summarization is a process to reduce the volume of text documents using computer programs to create a text summary with keeping the key terms of the documents. Due to cumulative growth of information and data, automatic text summarization technique needs to be applied in various domains. The approach helps in decreasing the quantity of the document without changing the context of information. In this paper, the proposed Persian text summarizer system employs combination of graph-based and the TF-IDF methods after word stemming in order to weight the sentences. SA-GA based sentence selection is used to make a summary, and once the summary is created. The SA-GA is a hybrid algorithm that combines Genetic Algorithm (GA) and Simulated Annealing (SA). The fitness function is based on three following factors: Readability Factor, Cohesion Factor, and Topic-Relation Factor. Evaluation results demonstrated the efficiency of the proposed system.