Dayiheng Liu (刘大一恒)
Results
2
comments of
Dayiheng Liu (刘大一恒)
> Hi, I wanted to augment the squad 1.0 dataset (not unanswerable questions). I trained a standard roberta MRC model using the transformers library which was giving 86.16 and 92.31...
> Hi, 1) we trained the autoencoder on the 2M corpus that you provide replacing the "train_file" in this script https://github.com/dayihengliu/CRQDA/blob/master/crqda/run_train.sh. > 2) I will experiment with lower step sizes....