In this paper we address the automatic text summarization task. Text Summarization was showed to be an improvement over manually summarizing the large data. It summarizes the salient features from the text by preserving the content and serves the meaningful summary. To design an algorithm that can summarize a document by extracting key text and attempting to modify this extraction using a thesaurus and to reduce a given body of text to a fraction of its size, maintaining coherence and semantics. This summarization method can be done in natural language processing approach integrated with rule mining.