A term is significant if it happens over and over in a very doc. But that creates a problem. Words like “a” and “the” seem frequently. And as such, their TF rating will always be superior. The goal of argument mining is the automatic extraction and identification of argumentative structures https://spencerqeozz.bloggip.com/36998767/the-smart-trick-of-conversational-ai-that-nobody-is-discussing