بهبود خلاصه سازی خودکار متون فارسی با استفاده از روش‌های پردازش زبان طبیعی و گراف شباهت

A significant amount of available information is stored in textual databases which contains a large collection of documents from different sources (such as news, articles, books, emails and web pages). The increasing visibility and importance of this class of information motivates us to work on having better automatic evaluation tools for textual resources. The automatic summarization of text is one of the ways to prevent the waste of users’ time. The extractive text summarization consists of the extraction of the more important sentences with the purpose of shortening input text while maintaining the topics covered and the subjects discussed. In this paper, we have tried to improve the accuracy of the extracted summaries by combining natural language processing and text mining techniques. By modifying the mentioned algorithms and sentence scoring measures, accuracy is increased as compared to the previously used techniques. Part of speech tagging is used for calculating coefficient of words’ importance. Using this approach will in turn help us with to pick the more meaningful words and phrases that will result in better accuracy of the system. Graph similarity‘s methods are used to select sentences. Changing weight of the selected sentences in each step leads to solve the redundancy problem. Standard evaluation measures such as “Precision” and “Recall” are used to evaluate results based on a Persian corpus.