There are many articles about applications of VAE such as image reconstruction, denoising, data compression / augmentation. However, I have not seen an example of embeddings for high dimensional data such as words.

Are there some papers about the use of VAE as embedding constructers ?

If there are, how do these deep embeddings compare with shallow technics such as Word2vec and other Skip-gram / Bag-of-words?

  • 2
    $\begingroup$ I upvoted this because it is a good question but please edit your title to something more informative. As it stands it is very broad. $\endgroup$ – usεr11852 Apr 28 '19 at 21:31

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.