Word2Vec PlotΒΆ

word2vec embedding with R. metric

3,000,000 words and phrases mapped by word2vec using Google News into 300 dimensions. The data was then embedded into 2 dimensions using Spectral Embedding. The plot shows a sample of 10,000 points displaying the overall shape of the embedding as well as the estimated “stretch” (i.e. dual push-forward Riemannian metric) at various locations in the embedding.