Parameter estimation has been studied quite extensively in standard mixture models.

However,DBNsonly allow for a fixed chain of Markov dependencies between time slices and cannot represent nested hierarchicalstructures.

Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but alsosentence-levelstochastic temporaltransitions.