TL;DR该研究介绍了一种针对文档群集的Hierarchical Dirichlet process (HDP)模型，描述了一种新的split-merge MCMC采样算法用于后验推断，这种算法可以显著改善传统的Gibbs采样，并且给出了一些因数据属性而导致的改进理解。
Abstract
The hierarchical dirichlet process (HDP) has become an important bayesian nonparametric model for grouped data, such as document collections. The HDP is used to construct a flexible mixed-membership model where t