This tool visualizes the basic working mechanism of word2vec, a popular word embedding model, originally published by Mikolov et al. word2vec. It is the result of a few days’ hack during his preparation for the a2-dlearn (Ann Arbor Deep Learning Meetup) event hosted by Daniel Pressel.

Here are the slides of his talk. To read more about this work, please read the paper explaining the parameter learning of word embedding. He is planning to keep adding functionalities to the tool, and it is greatly appreciated if you could help in the development process! The repository is at Wevi live demo.