The world of text is increasing considerably. Hence, a successful summarization technology has a key role to play in the future of computing. This paper presents an efficient method of intelligently generating summaries, which uses operations derived from an analysis of human written abstracts. The algorithm uses both statistical and semantic based heuristics to produce cohesive extracts. In the proposed system, an efficient method for evaluating lexical chains as an intermediate step has been used. We have also introduced a method for finding text cohesion and implemented the same in the summarizer. The proposed summarizer also edits long extracted sentences, using reduction to remove non essential phrases. The system has been implemented using JAVA standard Development kit. Copyright © IICAI 2005.