Review for NeurIPS paper: Bayesian Attention Modules

This paper proposes considering attention mechanisms as continuous latent variables, using VAEs for training. It uses reparametrizable distributions such as Weibull and log-normal distributions to get unnormalized weights, which are then normalized. Experiments show that the proposed continuous latent attention mechanism gets better performance compared to deterministic attention on a wide variety of tasks, including image captioning, machine translation, graph classification, and fine-tuning BERT. All reviewers recommended acceptance, pointing out that this is an interesting idea and a solid and well-executed work. One concern was raised about the significance of improvement on VQA and NMT, and about directly setting prior to approximate posterior, which the authors addressed in the rebuttal.