Abstract: Research in Automatic text summarization systems has gained momentum in recent times mostly due to the advances in natural language processing libraries and techniques. In this work, we have proposed a graph based approach for automatic text summarization. This approach uses the concept of computing how closely, significant words in a sentence are related to each other. This metric further weighs the significance of the sentences in the text document. NLTK library for python is used to build the automatic text summarization system based on this approach. The results obtained show that this technique is effective in producing high quality summaries.

Keywords: Automatic Text Summarization, Extractive Summarization, Natural Language Processing, NLTK Library.