Reviews: Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks

Making recommendations by exploiting the plethora of text data that accompanies products seems like an under-explored area, especially using recent advances in deep language models. I commend the authors for contributing to this research direction. The CRAE seems to work well (at least in recall at k), performing at a high level on two real-world datasets. However, I think this paper would be a better fit for a more applied conference, such as KDD or RecSys, because there is little novelty to the model's core components. I'll address each individually, in order of (my perceived) importance: 1) Robust Recurrent Networks (RRN): The proposed RRN uses distributional activations that are backpropagated through directly.