12b1e42dc0746f22cf361267de07073f-AuthorFeedback.pdf

We thank all reviewers for constructive comments. We added an ablation study on the SCAN length split to demonstrate its importance. For example, in the test set, there is a new pattern "jump around right thrice" that does not appear in the training set. Recursion and sequence manipulation supported by NeSS are critical to learn such parsing rules to generalize. NeSS is 100% in 2 runs, and 62.5% in 3 runs. When the model predicts the alternative translation, the exact match accuracy becomes lower.