State Space LSTM Models with Particle MCMC Inference
Xun Zheng, Manzil Zaheer, Amr Ahmed, Yu-An Wang, Eric P. Xing, Alexander J. Smola
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
Long Short-Term Memory (LSTM) is one of the most powerful sequence models. Despite the strong performance, however, it lacks the nice interpretability as in state space models. In this paper, we present a way to combine the best of both worlds by introducing State Space LSTM (SSL) models that generalizes the earlier work zaheer2017latent of combining topic models with LSTM. However, unlike zaheer2017latent, we do not make any factorization assumptions in our inference algorithm. We present an efficient sampler based on sequential Monte Carlo (SMC) method that draws from the joint posterior directly. Experimental results confirms the superiority and stability of this SMC inference algorithm on a variety of domains.