The provided code might have a mismatch with the paper

Complex-data / ERRA

6 stars 1 forks source link

The provided code might have a mismatch with the paper #2

Open zyrmj0212 opened 1 year ago

zyrmj0212 commented 1 year ago

Hi, Thanks for sharing the code. However, I noticed that the loss function in the code misses the aspect discriminator loss (Equation (8) in the paper). And there's an additional context_predition loss originally from the PETER model. May you explain the reason for that?

Complex-data commented 6 months ago

Regarding aspect loss, we refer to the sixteenth part of the formula in this article https://www.ijcai.org/proceedings/2019/0296.pdf