Is there an effective way of obtaining the topic distribution for a given document from a Variational AutoEncoder Latent Dirichlet Allocation (VAE-LDA)?

Most existing public VAE-LDA codebases seem to only output top words for each topic.

The repositories that I'm looking at are:

  1. https://github.com/rzTian/RRT-VAE
  2. https://github.com/hyqneuron/pytorch-avitm

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.