Re: discussion/comparison: We have tried to provide both experimental and analytical discussion about word-level

We thank the reviewers for their in-depth reviews, and will use them to make the final version as clear as possible. We will correct the missing notations and typos, we apologize for these oversights. We have reported perplexity per word consistent with prior work; we wil clarify the equation. Dirichlet prior distribution parameter is 0.5. We will report these in the experiments section.