INNER CODE UNIT · Python
f1
microsoft/AzureML-BERT · finetune/evaluate_squad.py:38
f1 = (2 * precision * recall) / (precision + recall)
return f1
def exact_match_score(prediction, ground_truth):
return (normalize_answer(prediction) == normalize_answer(ground_truth))
def metric_max_over_ground_truths(metric_fn, prediction, ground_truths):
scores_for_ground_truths = []
for ground_truth in ground_truths:
score = metric_fn(prediction, ground_truth)
scores_for_ground_truths.append(score)
return max(scores_for_ground_truths)
def evaluate(dataset, predictions):
f1 = exact_match = total = 0