F1 Score for ranking task 2 and 3

[trenusch]

Why are the accuracy and f1 score are always the same in the evaluation of submissions for task 2 and task 3?

[good-good-study]

For multiclass classification, micro-f1, micro-precision, micro-recall and accuracy are always the same, since we always recall one and only one label for each sample.

[xuange_cui]

The metrics in the leaderboard of task 2 & 3 seems strange

There are two metrics in the leaderboard of task 2& 3, f1 score and accuracy. Surprisingly, their values are the same. I think that f1 score doesn’t work, only the accuracy is given. Am I correct?