I use ANN to predict words from words. The input and output are all words vectors. I do not know how to get words from the output of ANN. By the way, it's gensim I am using
You can find cosine similarity of the vector with all other word-vectors to find the nearest neighbors of your vector.
The nearest neighbor search on an n-dimensional space, can be brute force, or you can use libraries like FLANN, Annoy, scikit-kdtree to do it more efficiently.
update
Sharing a gist demonstrating the same: https://gist.github.com/kampta/139f710ca91ed5fabaf9e6616d2c762b
来源：https://stackoverflow.com/questions/35914287/word2vec-how-to-get-words-from-vectors