add Rouge score

[karthikrangasai]

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?

Fixes #51 .

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 🙃

[codecov]

Codecov Report

Merging #399 (218418f) into master (b1062c9) will decrease coverage by 0.39%.
The diff coverage is 82.82%.

@@            Coverage Diff             @@
##           master     #399      +/-   ##
==========================================
- Coverage   96.45%   96.05%   -0.40%     
==========================================
  Files         120      122       +2     
  Lines        3804     3900      +96     
==========================================
+ Hits         3669     3746      +77     
- Misses        135      154      +19     

Flag	Coverage Δ
Linux	75.51% <38.38%> (-0.99%)	⬇️
Windows	75.51% <38.38%> (-0.99%)	⬇️
cpu	96.05% <82.82%> (-0.35%)	⬇️
gpu	?
macOS	96.05% <82.82%> (-0.35%)	⬇️
pytest	96.05% <82.82%> (-0.40%)	⬇️
python3.6	95.25% <82.82%> (-0.33%)	⬇️
python3.8	96.05% <82.82%> (-0.35%)	⬇️
python3.9	95.94% <82.82%> (-0.35%)	⬇️
torch1.3.1	95.25% <82.82%> (-0.33%)	⬇️
torch1.4.0	95.33% <82.82%> (-0.33%)	⬇️
torch1.9.0	95.94% <82.82%> (-0.35%)	⬇️

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

Impacted Files	Coverage Δ
torchmetrics/text/rouge.py	70.73% <70.73%> (ø)
torchmetrics/functional/text/rouge.py	90.19% <90.19%> (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	82.50% <100.00%> (+0.92%)	⬆️
torchmetrics/functional/regression/spearman.py	93.33% <0.00%> (-4.45%)	⬇️

---

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 b1062c9...218418f. Read the comment docs.

[Borda]

can we rather use only rouge_score only for testing and have our own implementation?

[SkafteNicki]

just some initial comments

[karthikrangasai]

The import errors will be gone after #383 is merged and rouge-score is added as a text dependency because it will install it before the imports are checked for.

[Borda]

@karthikrangasai how is it going? the mentioned PR has been merged... 🐰

[karthikrangasai]

I have updated the dependencies but the pkg-install test fails for some reason. I don't know why it is not able to import rouge_scorer.

[SkafteNicki]

okay, final set of comments :]

[Borda]

@karthikrangasai mind add typing? (mypy is failing)

[awaelchli]

wow that's a very old feature request <3

I mainly looked over the docs, very nice!