Question about baselines

Dear authors of the HYPRO,

Thank you for publishing the paper and sharing the official implementation of the method!

I try to understand the experimental setup and come to the following questions:
1. How can I reproduce the results for baseline methods (NHP, DualTPP, etc.)?
2. Did you use sampling or maximum likelihood prediction for the baselines?
3. Did you compare the proposed rescoring method with a beam search?

Looking forward to your reply and would be very grateful for any clarifications.