Supervised Hierarchical Dirichlet Processes with variational inference

We present an extension to the Hierarchical Dirichlet Process (HDP), which allows for the inclusion of super-vision. Our model marries the non-parametric benefits of HDP with those of Supervised Latent Dirichlet Allocation (SLDA) to enable learning the topic space directly from data while simultaneously including the labels within the model. The proposed model is learned using variational inference which allows for the efficient use of a large training dataset. We also present the online version of variational inference, which makes the method scalable to very large datasets. We show results comparing our model to a traditional super-vised parametric topic model, SLDA, and show that it out-performs SLDA on a number of benchmark datasets. 1