WeiYuan

> * I think 14 bleu4 score is reasonable performance, because neural question generation models are not generalized well to other dataset. > * You can find sentence level qg...

> The training data is here: > https://github.com/lin-tan/CoCoNut-Artifact/releases/tag/training_data_1.0.0 I am confused with the form of your files. I mean, the code in your project read the data as "prefix =...