f52db9f7c0ae7017ee41f63c2a7353bc-AuthorFeedback.pdf

We thank the reviewers for the valuable feedback and address specific comments below. Kim et al. [2019] uses attention to aggregate information of the context data and relates target In terms of actual running time, our method compares much more favorably with all the baselines above. We will include these larger-scale experiments in the revised version. Note that our model's complexity can be further reduced to It was presented in Appendix C. We will improve the presentation to make it more accessible. In all experiments, we normalize the data input and output.