The paper received mixed reviews from four reviewers. All the reviewers generally agree the paper is interesting and exposes an interesting research direction, which comes naturally to humans, but is currently lacking in most modern machine learning systems today. The main concerns raised by the reviewers are due to synthetic data and a missing concrete proposal for how to incorporate mutual exclusivity into the model as an inductive bias. The AC believes synthetic data is not sufficient reason for rejection because ultimately machine learning systems need to work on all cases. Several other minor concerns are also raised (architecture search, no other model has ME), but those reasons are minor and not sufficient weaknesses directly related to the contribution. The author rebuttal clarified the points about synthetic data and missing concrete proposal, and there was discussion among the reviewers. The reviewers did not reach consensus. The AC examined the paper closely, and agrees with the reviewers that this paper could stimulate interesting research findings. While there is no concrete proposal for how to fix the problem, exposing limitations, especially ones that are overlooked, are valuable contributions to the community, and are likely to spur follow-up work. The AC therefore recommends the paper for acceptance.