Implementing data augmentation from TinyBERT

[MichelBartels]

Is your feature request related to a problem? Please describe.
A basic version of model distillation was implemented with #1758. However, there is still room for improvement. The TinyBERT paper (https://arxiv.org/pdf/1909.10351.pdf) details an approach for finetuning an already pretrained small language model.

Describe the solution you'd like
Adding the functionality to generate more data samples by using approach outlined in TinyBERT paper. This could be implemented as an additional DataSilo.

Describe alternatives you've considered
https://arxiv.org/pdf/1910.08381.pdf: Seems to depend too heavily on expensive retraining and seems to be too task specific.
https://arxiv.org/pdf/2002.10957.pdf, https://arxiv.org/pdf/1910.01108.pdf: Seem only to focus on pretraining

Additional context
This is the second of two issues for implementing finetuning as described in the TinyBERT paper. This issue focusses on data augmentation. The first issue focussed on the loss functions.