Multi-Source Neural Translation

2016/01/05 by Barret Zoph, Kevin Knight, Zoph, Barret +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #cs.CL

paper · pdf · doi:10.48550/arxiv.1601.00710

5 pages, 6 figures

arxiv created 2016/01/05 · arxiv updated 2016/01/06

Abstract

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.

Related

• Multi-Source Syntactic Neural Machine Translation
• Multi-channel Encoder for Neural Machine Translation
• Neural Machine Translation by Jointly Learning to Align and Translate
• Mutual Information and Diverse Decoding Improve Neural Machine Translation
• Enabling Multi-Source Neural Machine Translation By Concatenating Source Sentences In Multiple Languages