Michael Shieh

You can lower the temperature. Please refer to the README for more information. As a sanity check, you can set the temperature to 0 and the model should generate perfectly...

Hi, I haven't tried it before because there are no unlabeled data for it. Did you use part of the training set as the unlabeled data? If I were you,...

You can also try a simpler data augmentation SwitchOut, which replace words with words randomly sampled from your vocabulary.

Hi, it depends on whether you use BERT or not. When BERT is used, the model converges to a good accuracy fairly quickly, so we only generate one paraphrase for...

You can use the same code for your dataset. But I am not sure if back translation would work well there.

I am not sure what's the problem.. It seems to run correctly on linux. Are you using linux?

I do see a file called "graph.pbtxt" when running the code. Not sure if this would give the graph definition. You might need to write the summery writer yourself.

Hi, if you only have 35 data points in the real world domain, you might need to design some prior knowledge to filter out synthesised data points. If you have...

I can't say for sure. I haven't tried similar settings. It's worth a try.

1. Sorry for the confusion. 1.3M means 1.3 Million 2. Right.