search

patverga / bran

Full abstract relation extraction from biological texts with bi-affine relation attention networks
Apache License 2.0
128 stars 33 forks source link

Why do you seperate positive and negative examples? #2

Closed FrankWork closed 6 years ago

FrankWork commented 6 years ago

hi, I'm confused. Why do you separate positive and negative examples? Why not mix them together and shuffle?

patverga commented 6 years ago

This was done to balance the classes because the negative class is much larger than the positive classes. Addressing class imbalances is important for improving recall of the minority classes. At each step, we sample either a positive or negative batch with equal probability.

There are other ways one could address this. For example, as you suggested, you could mix all samples together and then down weight the loss for negative samples. This is an equally valid strategy and would just require some tuning to calibrate with the existing hyper-parameters.

FrankWork commented 6 years ago

Thanks a lot. I finally got it.