Merge pull request microsoft#572 from microsoft/staging

Staging to Master

Merge pull request microsoft#540 from microsoft/staging

Staging to Master

remove bert initialization into MTDNNModel

Merge pull request microsoft#506 from microsoft/staging

Staging to master

Staging to master to add the latest fixes (microsoft#503)

* update mlflow version to match the other azureml versions

* Update generate_conda_file.py

* added temporary

* doc: update github url references

* docs: update nlp recipes references

* Minor bug fix for text classification of multi languages notebook

* remove bert and xlnet notebooks

* remove obsolete tests and links

* Add missing tmp directories.

* fix import error and max_nodes for the cluster

* Minor edits.

* Attempt to fix test device error.

* Temporarily pin transformers version

* Remove gpu tags temporarily

* Test whether device error also occurs for SequenceClassifier.

* Revert temporary changes.

* Revert temporary changes.

Merge pull request microsoft#437 from microsoft/staging

Staging to Master

Merge pull request microsoft#413 from microsoft/staging

Staging