A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
We propose a novel neural topic model in the Wasserstein autoencoders (WAE) framework. Unlike existing variational autoencoder based models, we directly enforce Dirichlet prior on the latent document-topic vectors. We exploit the structure of the latent space and apply a suitable kernel in minimizing the Maximum Mean Discrepancy (MMD) to perform distribution matching. We discover that MMD performs much better than the Generative Adversarial Network (GAN) in matching high dimensional Dirichletdoi:10.18653/v1/p19-1640 dblp:conf/acl/NanDNX19 fatcat:hqanr3yzmfbdvj32jrc5vbr6mu