Tweeted By @PyTorch

New seq2seq architecture - jointly encodes source and targets into a 2D ConvNet. No enc/dec or explicit attention.
Outperforming ConvS2S and Transformers on IWSLT'14 de<->en, with 3 to 8 times less parameters
from @melbayad and teamhttps://t.co/8NmiwmnhI2https://t.co/LqUYynj8vB pic.twitter.com/KFdcucErHI

— PyTorch (@PyTorch) August 27, 2018