Text Summarization Based on Several Natural Language Techniques

Abstract

Because of the great amount of information that provided by internet technologies, the automatic text summarization have become more important. This paper describes a method for summarizing English text. It depends on extractive summarization. The method implies many techniques of statistics and linguistic approaches especially based on morphological rules. The linguistic approaches in this method also include synonym, word-frequencies, word position, and part of speech. It will be shown that merging many statistics and linguistic approaches in one system, gives high accurate results at low threshold values. The system is tested to find the best threshold value, and it was 60%.