A T(G) A T(B) LevT(O) LevT(T)26.89 27.60 25.18 27.03 It1 2 3 4 5 6 7 8 9 10 2.43% 12.3 48.1 28.5 8.5 2.0 0.4 0.1 0 0 0.1 A VG

We thank all the reviewers' insightful suggestions. We will add SoT A numbers in the final version as R3 suggested. We will remove it in the final version. We've updated Figure 4 (a) using the new Figure 6 (in the Appendix), we see that the average number of iterations grows slowly with the sentence length. Why learning from teacher is better than oracle?