In the context of Natural Language Processing (NLP) systems, word vectorization is the process of mapping words or phrases to a vector across the different dimensions of how a word can be represented based on similarities, semantics, and relationships. The vector, which is a line connecting two points in different dimensions, encodes the meaning of a word such that the words that are closer in the vector space are most probably similar in meaning. Using machine learning approaches, machines can learn how words are related or have similar meaning. Similar words occupy locations close to each other in vector space, whereas words that are dissimilar are far apart. These features can include context, such as when words are used in conjunction or near other words.