Hierarchical Topic Models and the Nested Chinese Restaurant Process

We address the problem of learning topic hierarchies from data. The model selection problem in this domain is daunting—which of the large collection of possible trees to use? We take a Bayesian approach, generating an appropriate prior via a distribution on partitions that we refer to as the nested Chinese restaurant process. This nonparametric prior allows arbitrarily large branching factors and readily accommodates growing data collections. We build a hierarchical topic model by combining this prior with a likelihood that is based on a hierarchical variant of latent Dirichlet allocation. We illustrate our approach on simulated data and application to the modeling of NIPS abstracts.

• Type: Conference
• Year: 2003
• Where: NIPS
• Authors: David M. Blei, Thomas L. Griffiths, Michael I. Jordan, Joshua B. Tenenbaum
• Keywords: Hierarchical Topic Model, Model Selection Problem, NIPS 2003, NIPS 2007, Nonparametric Prior Allows