Multi-Source Neural Translation

01/05/2016

∙

by   Barret Zoph, et al.

∙

0

∙

share

We build a multi-source machine translation model and train it to maximize the probability of a target English string given French and German sources. Using the neural encoder-decoder framework, we explore several combination methods and report up to +4.8 Bleu increases on top of a very strong attention-based neural translation model.