Beta-Negative Binomial Process and Exchangeable Random Partitions for Mixed-Membership Modeling
This work addresses the need for efficient and accurate topic modeling in text analysis, representing an incremental improvement over existing nonparametric Bayesian methods.
The paper tackled the problem of modeling mixed-membership data by developing an exchangeable partition probability function for the beta-negative binomial process (BNBP), enabling explicit clustering without truncation. This resulted in a novel nonparametric Bayesian topic model with state-of-the-art predictive performance, featuring simple implementation and fast convergence.
The beta-negative binomial process (BNBP), an integer-valued stochastic process, is employed to partition a count vector into a latent random count matrix. As the marginal probability distribution of the BNBP that governs the exchangeable random partitions of grouped data has not yet been developed, current inference for the BNBP has to truncate the number of atoms of the beta process. This paper introduces an exchangeable partition probability function to explicitly describe how the BNBP clusters the data points of each group into a random number of exchangeable partitions, which are shared across all the groups. A fully collapsed Gibbs sampler is developed for the BNBP, leading to a novel nonparametric Bayesian topic model that is distinct from existing ones, with simple implementation, fast convergence, good mixing, and state-of-the-art predictive performance.