Document Summarization has become a vital task for various individuals and businesses that require a way of cutting down complexities involved with bulky documents. Summarization reduces a piece of document to a rendition less lengthy. This reduces the time complexity and effort initially required to consume that text. This is done such that the original message in the document is retained.
Problem Statement
Many times, readers do not require to read the entire article due to various reasons like time management. A way out is to read a summarized version. This is not always available to readers. A way out is to be able to generate a summarized version. In this project, we will tackle this problem by implementing document summarization using Python and Natural Language Processing techniques. This can summarize any English document and print out a summarized copy. We will source our articles from Wikipedia using beatifulsoup library for scraping web content which is available for easy scraping of pages from the site. The article can be found here: https://en.wikipedia.org/wiki/History_of_Poland_(1945%E2%80%931989)