massive icon indicating copy to clipboard operation
massive copied to clipboard

Published 20 hours ago • verified publisher icon alexa

About the official evaluation script

Open bozheng-hit opened this issue 2 years ago • 2 comments

Is there an evaluation script that can directly compare a prediction file against the gold prediction file, i.e., the official evaluation script?

bozheng-hit avatar Jul 16 '22 07:07 bozheng-hit

Hi @bozheng-hit, recommend using eval.ai for official test results. We will be opening submissions to the MMNLU-22 phases soon.

massive-dev-amz avatar Jul 20 '22 17:07 massive-dev-amz

Hi @bozheng-hit, recommend using eval.ai for official test results. We will be opening submissions to the MMNLU-22 phases soon.

Is it possible to return results for all languages separately?

bozheng-hit avatar Jul 27 '22 04:07 bozheng-hit