Hands-On Machine Learning with C++

Word2Vec

In 2013, Tomash Mikolov proposed a new approach to word embedding, which he called Word2Vec. His approach is based on another crucial hypothesis, which in science is usually called the distributional hypothesis or locality hypothesis: words that are similar in meaning occur in similar contexts (Rubenstein and Goodenough, 1965). Proximity measure, in this case, is understood very broadly as the fact that only semantically similar words can be in proximity. For example, the phrase clockwork alarm clock is acceptable in this model, but clockwork orange is not. The words clockwork and orange can't be easily combined by semantics. The model proposed by Mikolov is very simple (and therefore useful)—we predict the probability of a word ...