Add the CRF model wrapper

[howl-anderson]

Description

Brief Description of the PR:

Add the CRF model wrapper.

It can be used like following:

tag_num = ... # number of tags
base_model = build_base_model(...)
model = CRFModelWraper(base_model, tag_num)

# CRFModelWraper is a subclass of tf.keras.Model
# so we can compile / fit / evaluate as normal model

# NOTE: CRF loss is computed inside the model, so we do not specific the loss for crf
model.compile(...)
model.fit(...)

Fixes # (issue)

Type of change

• Bug fix
• New Tutorial
• Updated or additional documentation
• Additional Testing
• New Activation and the changes conform to the activation contribution guidelines
• New Callback and the changes conform to the callback contribution guidelines
• New Image addition and the changes conform to the image op contribution guidelines
• New Layer and the changes conform to the layer contribution guidelines
• New Loss and the changes conform to the loss contribution guidelines
• New Metric and the changes conform to the metric contribution guidelines
• New Optimizer and the changes conform to the optimizer contribution guidelines
• New RNN Cell and the changes conform to the rnn contribution guidelines
• New Seq2seq addition and the changes conform to the seq2seq contribution guidelines
• New Text addition and the changes conform to the text op contribution guidelines

Checklist:

• I've properly formatted my code according to the guidelines
  • By running Black + Flake8
  • By running pre-commit hooks
• This PR addresses an already submitted issue for TensorFlow Addons
• I have made corresponding changes to the documentation
• I have added tests that prove my fix is effective or that my feature works
• This PR contains modifications to C++ custom-ops

How Has This Been Tested?

If you're adding a bugfix or new feature please describe the tests that you ran to verify your changes:
*

[howl-anderson]

@gabrieldemarmiesse You are one of the most suitable reviewers for this PR. So please take a look. Thank you!

[bhack]

@gabrieldemarmiesse You are one of the most suitable reviewers for this PR. So please take a look. Thank you!

I don't think he is still active in the project.

[howl-anderson]

@bhack Thank you for your kindly remind. Do you have any reviewer to recommend for this PR? Or could it possible to grant write permission to me? So, I can merge it to the repo. There are a few CRF related PRs still waiting for review for more than two weeks but no one response yet. If I have the write permission, I can merge them too. Of course, I am the codeower of those CRF related features, so I will continuously bugfix and improve them.

/cc @seanpmorgan