Verify evals on Papers with Code

Hi,

Niels here from the open-source team at Hugging Face. Congratulations on your work!

I've made the [paper](https://paperswithcode.co/paper/2103.06874) and [2 paper-native evaluations](https://paperswithcode.co/paper/2103.06874#results) available on Papers with Code.

The paper is part of the [Named Entity Recognition](https://paperswithcode.co/tasks/named-entity-recognition) task page.

The CANINE-C + n-grams result currently ranks first on [MasakhaNER](https://paperswithcode.co/benchmark/masakhaner?task=named-entity-recognition&eval=5913).

The CANINE-C + n-grams result currently ranks fourth on [CoNLL NER](https://paperswithcode.co/benchmark/conll-ner?task=named-entity-recognition&eval=5912).

Would it be possible to verify these results and let me know if any score, model name, benchmark protocol, or openness metadata should be corrected?

You can also edit the task, methods, project page, and GitHub URL directly from the paper page using your Hugging Face account.

If you'd like to showcase the results in your repository README, you can copy these live leaderboard badges (or use the “Copy PwC badge” button in the Results section):

[](https://paperswithcode.co/api/v1/papers/2103.06874/leaderboard-badge-link?eval=5913)

Kind regards,

Niels

Start with the linked paper and its two Papers with Code evaluation pages for MasakhaNER and CoNLL NER. Compare the published scores, model name, benchmark protocol, and openness metadata; done means discrepancies are identified and the relevant result or project metadata is corrected or confirmed.

Written by the indexing model from the issue text.