Ex3 Evaluation #149

Unanswered

Qrauli asked this question in Advanced IR: Exercise Q&A

Qrauli
May 21, 2024

Hello,
I have two questions regarding the third part of the exercise.

How exactly are we supposed to evaluate the model if there are multiple answers possible? Should we just get the max overlap value (exact, f1) over all answers?
What exactly are we supposed to store at the end? The average f1/exact overlap of the whole dataset?

Replies: 0 comments

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment