How to evaluate other versions of MultiWOZ dataset

[mrghofrani]

This is more a question than a bug or something else, I have seen the documentation (The Readme.md file) and the codes, but I can't understand how to evaluate the predictions which have been generated from other versions of the MultiWOZ dataset. As you know MultiWOZ dataset has three main versions (2.0, 2.1, and 2.2), The code seems to be implemented to just evaluate the predictions for the 2.2 version.