GeondoPark

Factors that improved the performance on RTE and SQuAD 2.0.

3

Hi, huawei-noah team. Thank you for sharing the code of your interesting work, TinyBERT. I wonder which factors resulted in the performance improvement on the RTE and SQuAD 2.0 datasets,...

Hi, Thank you for your interesting work! I just wondering why don`t you used the pooler for only KD.Full and if you use the pooler, did you initialize the pooler...

Hi, thanks for publishing the paper and sharing the source code. I found that the "attn_output" is not used after definition. When learning roberta for parameter efficient learning, the paper...

Hi, First of all, Thank you so much for sharing the code. Maybe because of my lack of knowledge, I wonder that is there any difference between declaring an optimizer...

Could you share the evaluation metric code for each attribute map for accurate comparison for new algorithms?