Code and Data for our Findings of ACL 2021 paper titled 'Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation. Varun Gangal *, Harsh Jhamtani *, Eduard Hovy, Taylor Berg-Kirkpatrick'
Hi! First of all, thank you for sharing your work.
I hope to reproduce the results of SCARCE in a multi-reference setup. In this case, how should I set the value of --max_num_multi_response parameter? Is it okay to set the value as -1 (default)?