Timezone: »

 
Poster
Bidirectional Convolutional Poisson Gamma Dynamical Systems
wenchao chen · Chaojie Wang · Bo Chen · Yicheng Liu · Hao Zhang · Mingyuan Zhou

Thu Dec 10 09:00 PM -- 11:00 PM (PST) @ Poster Session 6 #1769

Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but also sentence-level stochastic temporal transitions. With word-level convolutions capturing phrase-level topics and sentence-level transitions capturing how the topic usages evolve over consecutive sentences, we aggregate the topic proportions of all sentences of a document as its feature representation. To consider not only forward but also backward sentence-level information transmissions, we further develop a bidirectional convolutional PGDS to incorporate the full contextual information to represent each sentence. For efficient inference, we construct a convolutional-recurrent inference network, which provides both sentence-level and document-level representations, and introduce a hybrid Bayesian inference scheme combining stochastic-gradient MCMC and amortized variational inference. Experimental results on a variety of document corpora demonstrate that the proposed models can extract expressive multi-level latent representations, including interpretable phrase-level topics and sentence-level temporal transitions as well as discriminative document-level features, achieving state-of-the-art document categorization performance while being memory and computation efficient.

Author Information

wenchao chen (Xidian university)
Chaojie Wang (Xidian University)
Bo Chen (Xidian University)
Yicheng Liu (Xidian university)
Hao Zhang (Cornell University)
Mingyuan Zhou (University of Texas at Austin)

More from the Same Authors