You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for this interesting work, and congratulations on the EMNLP acceptance! After reading the paper, one question I am having is that how those domain-specific templates are designed and selected. In the get_sst2_variant_template function (data_loaders.py), I see a couple of template candidates, so I guess what you did is to first manually design a couple of template candidates for each domain/task and then select the best one based on the dev set performance (if both dev and test sets exist), right? Please correct me if I am wrong and look forward to your reply. Thanks!
The text was updated successfully, but these errors were encountered:
Great question! That is indeed what we did, though the variants in the sst-2 template are from our template robustness experiments (which aren't on Arxiv yet, but will be very soon); for that, we used the templates from "Calibrate Before Use" https://arxiv.org/abs/2102.09690
Hi,
Thank you for this interesting work, and congratulations on the EMNLP acceptance! After reading the paper, one question I am having is that how those domain-specific templates are designed and selected. In the
get_sst2_variant_template
function (data_loaders.py
), I see a couple of template candidates, so I guess what you did is to first manually design a couple of template candidates for each domain/task and then select the best one based on the dev set performance (if both dev and test sets exist), right? Please correct me if I am wrong and look forward to your reply. Thanks!The text was updated successfully, but these errors were encountered: