Adding BERTScore metric

[gagan3012]

Before submitting

• Was this discussed/approved via a Github issue? (no need for typos and docs improvements)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure to update the docs?
• Did you write any new necessary tests?

What does this PR do?

This PR adds the BERTScore metric from its implementation here: https://github.com/Tiiiger/bert_score
Fixes #365 (issue).

PR review

Anyone in the community is free to review the PR once the tests have passed.
If we didn't discuss your PR in Github issues there's a high chance it will not be merged.

Did you have fun?

Make sure you had fun coding 🙃

[pep8speaks]

Hello @gagan3012! Thanks for updating this PR.

There are currently no PEP 8 issues detected in this Pull Request. Cheers! 🍻

Comment last updated at 2021-08-08 09:58:15 UTC

[codecov]

Codecov Report

Merging #424 (8801e64) into master (525642d) will decrease coverage by 21.30%.
The diff coverage is 71.73%.

@@             Coverage Diff             @@
##           master     #424       +/-   ##
===========================================
- Coverage   96.03%   74.73%   -21.31%     
===========================================
  Files         127      129        +2     
  Lines        4134     4179       +45     
===========================================
- Hits         3970     3123      -847     
- Misses        164     1056      +892     

Flag	Coverage Δ
Linux	74.73% <71.73%> (-0.04%)	⬇️
Windows	74.73% <71.73%> (-0.04%)	⬇️
cpu	74.73% <71.73%> (-21.23%)	⬇️
gpu	?
macOS	74.73% <71.73%> (-21.23%)	⬇️
pytest	74.73% <71.73%> (-21.31%)	⬇️
python3.6	?
python3.8	?
python3.9	?
torch1.3.1	?
torch1.4.0	?
torch1.9.0	?

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
torchmetrics/functional/text/bert.py	31.25% <31.25%> (ø)
torchmetrics/text/bert.py	92.30% <92.30%> (ø)
torchmetrics/__init__.py	100.00% <100.00%> (ø)
torchmetrics/functional/__init__.py	100.00% <100.00%> (ø)
torchmetrics/text/__init__.py	100.00% <100.00%> (ø)
torchmetrics/utilities/imports.py	82.92% <100.00%> (+0.42%)	⬆️
torchmetrics/utilities/distributed.py	17.24% <0.00%> (-81.04%)	⬇️
...ics/functional/classification/calibration_error.py	16.32% <0.00%> (-77.56%)	⬇️
torchmetrics/image/kid.py	20.22% <0.00%> (-76.41%)	⬇️
torchmetrics/image/inception.py	31.70% <0.00%> (-63.42%)	⬇️
... and 84 more

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 525642d...8801e64. Read the comment docs.

[Borda]

later we shall come with our own BERT implementation as the bert_score require heavy Transformers dependency