megagonlabs / ditto

Code for the paper "Deep Entity Matching with Pre-trained Language Models"
Apache License 2.0
256 stars 88 forks source link

How is your F1 score calculated, whether you use weight or macro or micro #12

Open zhouhuhq opened 3 years ago

oi02lyl commented 3 years ago

The task is binary (match or not match) with the match being the positive class. So the F1 score is the standard binary F1, e.g., https://scikit-learn.org/stable/modules/generated/sklearn.metrics.f1_score.html