Updated featurizers

[tabergma]

Proposed changes:

• Add option use_cls_token to all tokenizers. If it is set to True, the token __CLS__ will be added to the end of the list of tokens.
• Add option return_sequence to all featurizers. By default all featurizers return a matrix of size
  (1 x feature-dimension). If the option return_sequence is set to True, the corresponding featurizer will return a matrix of size (token-length x feature-dimension).
• Split featurizers into sparse and dense featurizers.
• Remove NGramFeaturizer. Please use CountVectorsFeaturizer instead.
• To use custom features in the CRFEntityExtractor use text_dense_features instead of ner_features. If text_dense_features are present in the feature set, the CRFEntityExtractor will automatically make use of them. Just make sure to add a dense featurizer in front of the CRFEntityExtractor in your pipeline and set the flag return_sequence to True for that featurizer.

closes #4957
part of https://github.com/RasaHQ/research/issues/54

Status (please check what you already did):

• added some tests for the functionality
• updated the documentation
• updated the changelog (please check changelog for instructions)
• reformat files using black (please check Readme for instructions)

[tmbo]

@tabergma you can change the model compatibility version in rasa/constants.py

[tmbo]

great work!

I've added some style suggestions but from my perspective this is ready to go

[tmbo]

woop woop 🎉