Closed jozef-mokry closed 8 years ago
Is the bias term c_tt required here: (https://github.com/nyu-dl/dl4mt-tutorial/blob/master/session3/nmt.py#L458) ? I think the softmax that follows will cancel the effect of that bias.
Hi @jozef-mokry , yes the bias term c_tt becomes obsolete but we keep it for backward compatibility (models trained before may cause problem with extra fields while loading)
c_tt
Is the bias term c_tt required here: (https://github.com/nyu-dl/dl4mt-tutorial/blob/master/session3/nmt.py#L458) ? I think the softmax that follows will cancel the effect of that bias.