Perhaps I'll explain this a bit better… Words can be converted into a vector representation by a word2vec algorithm . After conversion words will be a point in a high dimensional space. Relations between words will then be vectors between such points. Similar relations (or related relations)
Microsoft has unveiled an idea about a grammar and style tool for Word.  I proposed something similar for detecting problematic grammatical constructs in the content translation tools. It is a couple of years ago now, and I closed the task.