A Tutorial on Deep Latent Variable Models of Natural Language
arXiv: Computation and Language, Volume abs/1812.06834, 2018.
There has been much recent, exciting work on combining the complementary strengths of latent models and learning. Latent modeling makes it easy to explicitly specify model constraints through conditional independence properties, while learning makes it possible to parameterize these conditional likelihoods with powerful function appro...More
PPT (Upload PPT)