Table 2: 
For each language pair, we report the number of NMT systems trained on it, the oracle best BLEU we obtained, and its corresponding hyperparameter configuration.
Dataset#modelsBest BLEUbpe#layers#embed#hidden#att_headsinit_lr
zh-en 118 14.66 30k 4 512 1024 16 3e-4 
ru-en 176 20.23 10k 4 256 2048 8 3e-4 
ja-en 150 16.41 30k 4 512 2048 8 3e-4 
en-ja 168 20.74 10k 4 1024 2048 8 3e-4 
sw-en 767 26.09 1k 2 256 1024 8 6e-4 
so-en 604 11.23 8k 2 512 1024 8 3e-4 
Dataset#modelsBest BLEUbpe#layers#embed#hidden#att_headsinit_lr
zh-en 118 14.66 30k 4 512 1024 16 3e-4 
ru-en 176 20.23 10k 4 256 2048 8 3e-4 
ja-en 150 16.41 30k 4 512 2048 8 3e-4 
en-ja 168 20.74 10k 4 1024 2048 8 3e-4 
sw-en 767 26.09 1k 2 256 1024 8 6e-4 
so-en 604 11.23 8k 2 512 1024 8 3e-4 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept