Search code examples
tensorflowmachine-learningdeep-learningstanford-nlpreinforcement-learning

EM score in SQuAD Challenge


The SQuAD Challenge ranks the results against the F1 and EM scores. There is a lot of information about the F1 score (a function of precision and recall). But what would the EM score be?


Solution

  • Exact match. This metric measures the percentage of predictions that match any one of the ground truth answers exactly.

    According to here.