search

snap-stanford / GreaseLM

[ICLR 2022 spotlight]GreaseLM: Graph REASoning Enhanced Language Models for Question Answering
MIT License
228 stars 40 forks source link

RoBERTa Baseline #16

Open JohannaOm opened 4 months ago

JohannaOm commented 4 months ago

Hello, Thank you very much for providing the implementation of your model. I have a question regarding the Roberta baseline. Unfortunately, I could not find the implementation of Roberta baseline finetuning on in the QA tasks in the repository. Is it present in the repo, have I overlooked it? If not, what parameters were used for finetuning and how was the classification layer implemented? Many thanks in advance!

EchoDreamer commented 4 months ago

I have a problem with arisotoRoberta's reproduction of OBQA. The results are very much different from the original paper, so I hope the authors can provide me with the parameters, thanks!

JohannaOm commented 4 months ago

I have a problem with arisotoRoberta's reproduction of OBQA. The results are very much different from the original paper, so I hope the authors can provide me with the parameters, thanks!

Hello, could you reproduce the CSQA results with RoBERTa w/o KG?