Papers with Wasserstein objective

1 papers
Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling (N19-1)

Copied to clipboard

Challenge: Empirical experiments show that our model learns latent distributions that respect latent space geometry and is able to generate sentences that are more diverse.
Approach: They propose a Variational Wasserstein Autoencoder with Riemannian Normalizing Flow to solve this problem by transforming a latent variable into a space that respects the geometric characteristics of input space.
Outcome: Empirical results show that the proposed model avoids KLvanishing and has better performance in language modeling, likelihood approximation, and text generation tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations