Multi Reference ROUGEScore

[ashutoshml]

What does this PR do?

Fixes #667

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?

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 🙃
Yes.

[codecov]

Codecov Report

Merging #680 (f6b6ff9) into master (4f8015f) will decrease coverage by 0%.
The diff coverage is 91%.

@@          Coverage Diff          @@
##           master   #680   +/-   ##
=====================================
- Coverage      95%    95%   -0%     
=====================================
  Files         166    166           
  Lines        6379   6413   +34     
=====================================
+ Hits         6074   6103   +29     
- Misses        305    310    +5     

[stancld]

Dear @ashutoshml, thank you very much for your contribution. :] I left some minor comments. I will also need to consider averaging methods a bit more, but they're likely okay.

Also, I think you can update CHANGELOG.md with a note that we allow a user to evaluate against multiple references.

[ashutoshml]

Based on the current checks, it seems like the build is literally failing because of the absence of "Literal" typing in python<=3.7. Kindly let me know if it needs to be removed.

[stancld]

@ashutoshml Hi, Literal is not a part of typing for python<=3.7. You can, however, import Literal from typing_extensions, which is compatible with all python versions supported by TM.

[ashutoshml]

@ashutoshml Hi, Literal is not a part of typing for python<=3.7. You can, however, import Literal from typing_extensions, which is compatible with all python versions supported by TM.

Done. Hopefully, the errors would be resolved now.

[stancld]

@ashutoshml Nice, it looks good to me now. Also, thanks a lot for replacing List type annotations for more general Sequence annotations "]

[SkafteNicki]

LGTM

[ashutoshml]

Made the necessary changes from review comments. Not sure why the PyTorchLightning.metrics build is failing though.