EasyNLPnlp-393

Token Level Recall Generation

Problem

Generation recall is the multiset overlap divided by the number of reference tokens; return 0.0 when empty.

Given predicted and reference tokens, return the recall.

Hint

Divide the overlap by the reference size.

case 1

in: [["a","b","c"],["a","b"]]

expected: 1

case 2

in: [["x"],["y"]]

expected: 0

case 3

in: [["a"],[]]

expected: 0

Starter codePython

def token_level_recall_generation(predicted, reference):
    # Your code here
    pass

3 test cases · run your code against them in the editor