neuralmonkey
neuralmonkey copied to clipboard
Deep encoders and decoders
what the paper for this idea?
For example this one: https://arxiv.org/abs/1609.08144
Or https://arxiv.org/pdf/1606.04199.pdf
For WMT17 Edinburgh experimented with Deep networks and the Google one was not the best (I guess the system description is online soon)
The Edinburgh paper on deep architectures just came out today: https://arxiv.org/abs/1707.07631