Austin Matthews

Results 3 comments of Austin Matthews

Thanks for the feedback, Matthias! I updated the documentation. I talked to Graham about the mechanism of compute_attention() and update(). I agree that it would be nice to factor this...

Hmm, that's a good point. We still would need some sort of mechanism to have the ``Attender`` give some sort of initial state, and then some mechanism to get the...

Fixed in [this PR](https://github.com/neulab/xnmt/pull/569).