Skip to yearly menu bar Skip to main content


Poster

Convolutional Poisson Gamma Belief Network

CHAOJIE WANG · Bo Chen · SUCHENG XIAO · Mingyuan Zhou

Pacific Ballroom #237

Keywords: [ Approximate Inference ] [ Bayesian Deep Learning ] [ Bayesian Methods ] [ Generative Models ] [ Monte Carlo Methods ]


Abstract:

For text analysis, one often resorts to a lossy representation that either completely ignores word order or embeds each word as a low-dimensional dense feature vector. In this paper, we propose convolutional Poisson factor analysis (CPFA) that directly operates on a lossless representation that processes the words in each document as a sequence of high-dimensional one-hot vectors. To boost its performance, we further propose the convolutional Poisson gamma belief network (CPGBN) that couples CPFA with the gamma belief network via a novel probabilistic pooling layer. CPFA forms words into phrases and captures very specific phrase-level topics, and CPGBN further builds a hierarchy of increasingly more general phrase-level topics. For efficient inference, we develop both a Gibbs sampler and a Weibull distribution based convolutional variational auto-encoder. Experimental results demonstrate that CPGBN can extract high-quality text latent representations that capture the word order information, and hence can be leveraged as a building block to enrich a wide variety of existing latent variable models that ignore word order.

Live content is unavailable. Log in and register to view live content