Review for NeurIPS paper: Latent Template Induction with Gumbel-CRFs

This paper consider the text generation task in a VAE framework where the latent variables of a CRF are used as template of generation. The paper uses Gumbel-Softmax as the gradient estimator for the posterior distribution. As a reparameterized gradient estimator, the Gumbel-CRF gives more stable gradients than other gradient estimators such as REINFORCE and PM-MRF. The proposed method are tested in a variety of text modelling tasks. Reviewers agree this is an important and difficult problem.