lda2vec is an impressive and intuitional work combining LDA and word2vec together. The goal of lda2vec is to make volumes of text useful to humans (not machines!) while still keeping the model simple to modify. 
1.Their blog is https://multithreaded.stitchfix.com/blog/2016/05/27/lda2vec/#topic=38&lambda=1&term=
2.Their github link is 
https://github.com/cemoody/lda2vec

University of Michigan - Ann Arbor

Well-known LSA-based methods

https://en.wikipedia.org/wiki/Latent_semantic_analysis

Latent Semantic Analysis(LSA)-Reference

The Latent Dirichlet allocation (LDA) is a generative statistical model that allows sets of observations to be explained by unobserved groups that explain why some parts of the data are similar. It's actually a three level Bayesian model from words to themes to documents. Generally speaking, we consider a word in a document is selected by selecting a theme for this position first and selecting a word for the theme after that.

Latent Dirichlet allocation(LDA)

Probabilistic latent semantic analysis (PLSA), also known as probabilistic latent semantic indexing (PLSI, especially in information retrieval circles) is a statistical technique for the analysis of two-mode and co-occurrence data. Compared to standard latent semantic analysis which stems from linear algebra and downsizes the occurrence tables (usually via a singular value decomposition), probabilistic latent semantic analysis is based on a mixture decomposition derived from a latent class model.

Learn Before

Related