Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation

08/31/2017 ∙ by Toan Q. Nguyen, et al. ∙ 0

We present a simple method to improve neural translation of a low-resource language pair using parallel data from a related, also low-resource, language pair. The method is based on the transfer method of Zoph et al., but whereas their method ignores any source vocabulary overlap, ours exploits it. First, we split words using Byte Pair Encoding (BPE) to increase vocabulary overlap. Then, we train a model on the first language pair and transfer its parameters, including its source word embeddings, to another model and continue training on the second language pair. Our experiments show that transfer learning helps word-based translation only slightly, but when used on top of a much stronger BPE baseline, it yields larger improvements of up to 4.3 BLEU.



There are no comments yet.


page 1

page 2

page 3

page 4

Code Repositories


transfer learning in AI

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.