[Enhancement] Add whole word masking for BERT

[basicv8vc]

Description

Add whole word masking for BERT.

referred to bert link

Checklist

Essentials

• PR's title starts with a category (e.g. [BUGFIX], [MODEL], [TUTORIAL], [FEATURE], [DOC], etc)
• Changes are complete (i.e. I finished coding on this PR)
• All changes have test coverage
• Code is well-documented

Changes

• Feature1, tests, (and when applicable, API doc)
• Feature2, tests, (and when applicable, API doc)

Comments

• If this change is a backward incompatible change, why must this change be made.
• Interesting edge cases to note here

[codecov]

Codecov Report

Merging #770 into master will decrease coverage by 0.08%.
The diff coverage is 100%.

@@            Coverage Diff            @@
##           master    #770      +/-   ##
=========================================
- Coverage   90.49%   90.4%   -0.09%     
=========================================
  Files          66      66              
  Lines        6364    6370       +6     
=========================================
  Hits         5759    5759              
- Misses        605     611       +6

Impacted Files	Coverage Δ
src/gluonnlp/data/transforms.py	80.51% <100%> (+0.23%)	⬆️
src/gluonnlp/data/dataloader.py	83.62% <0%> (-5.18%)	⬇️

[mli]

Job PR-770/1 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-770/1/index.html

[mli]

Job PR-770/2 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-770/2/index.html

[mli]

Job PR-770/3 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-770/3/index.html

[mli]

Job PR-770/4 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-770/4/index.html

[mli]

Job PR-770/5 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-770/5/index.html

[eric-haibin-lin]

Great contribution! Let me know if my comment makes sense or not

[mli]

Job PR-770/10 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-770/10/index.html

[mli]

Job PR-770/11 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-770/11/index.html

[mli]

Job PR-770/12 is complete.
Docs are uploaded to http://gluon-nlp-staging.s3-accelerate.dualstack.amazonaws.com/PR-770/12/index.html

[eric-haibin-lin]

@basicv8vc thanks for the contribution!