Objective: For a large content of text file, we want to retrieve the most important information and summarize the content in a few lines of words. In other words, we want to reduce a large amount of data into a useful small amount of data by extracting the most important content. The data comes from the web in a specific field (e.g. political news, reports).
References: http://pakacademicsearch.com/pdf-files/sci/74/121-129.pdf http://thescipub.com/PDF/jcssp.2016.178.190.pdf http://cs229.stanford.edu/proj2013/ZhouMashuq-WebContentExtractionThroughMachineLearning.pdf