Text summarization involves generating a concise summary that includes crucial sentences and captures all the relevant information from the original text. There are two primary approaches to understanding summaries: extractive and abstractive. Extractive summarization seeks out parts of an article by searching for phrases or sentences that closely parallel already existing content in the text. It removes excessive content from the article while guaranteeing to sustain the original meaning of the document. As opposed to extractive, in this case authors pursue to understand context fully and then come up with new text based on that. In this comparison, it looks just how people are assimilating the material and how they would put it in words. Research on deep learning models has advanced significantly over the past century, and while it is promising, extractive summarization is still faster if applied appropriately, as it bypasses intrinsic difficulties in comprehension.