A Generic Approach to Topic Models

The benefit of this representation of topic models as "mixture networks" is its straight-forward mapping to inference equations and algorithms, which is shown with the derivation and implementation of a generic Gibbs sampling algorithm.

Abstract

This article contributes a generic model of topic models. To define the problem space, general characteristics for this class of models are derived, which give rise to a representation of topic models as "mixture networks", a domainspecific compact alternative to Bayesian networks. Besides illustrating the interconnection of mixtures in topic models, the benefit of this representation is ist straight-forward mapping to inference equations and algorithms, which is shown with the derivation and implementation of a generic Gibbs sampling algorithm.