tensorflow port of the lda2vec model for unsupervised learning of document + topic + word embeddings
TensorFlow implementation of Christopher Moody's lda2vec, a hybrid of Latent Dirichlet Allocation & word2vec
The lda2vec model simultaneously learns embeddings (continuous dense vector representations) for: * words (based on word and document context), * topics (in the same latent word space), and * documents (as sparse distributions over topics).
[ + integrated with the tf Embeddings Projector to interactively visualize results ]
Check back for updated docs and a walk-through example.
Meanwhile, read the paper and see the excellent README @ the original repo.