🚀 Feature request

Bart is a seq2seq model, but there might be applications where one would like to use only the pre-trained BartDecoder in an EncoderDecoder setting with a "long" encoder, such as

from transformers import EncoderDecoderModel

model = EncoderDecoderModel("allenai/longformer-large-4096", "facebook/bart-large")

# fine-tune model ...

This is already p

From paper, it mentioned

Instead, the training data generator chooses 15% of tokens at random, e.g., in the sentence my
dog is hairy it chooses hairy.

It means that 15% of token will be choose for sure.

From https://github.com/codertimo/BERT-pytorch/blob/master/bert_pytorch/dataset/dataset.py#L68,
for every single token, it has 15% of chance that go though the followup procedure.

Is your feature request related to a problem? Please describe.
For a fast proof of concepts users need to try Haystack on their own documents. While this is possible on the code level (e.g. Tutorial 1), in many cases an additional UI would be helpful so that users can interact more easily with the model and show it to colleagues.

Describe the solution you'd like
A minimal UI built wit

Issue to track tutorial requests:

• Deep Learning with PyTorch: A 60 Minute Blitz - #69