Data Augmentation for Low-Resource Neural Machine Translation

05/01/2017
by   Marzieh Fadaee, et al.
0

The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in computer vision, we propose a novel data augmentation approach that targets low-frequency words by generating new sentence pairs containing rare words in new, synthetically created contexts. Experimental results on simulated low-resource settings show that our method improves translation quality by up to 2.9 BLEU points over the baseline and up to 3.2 BLEU over back-translation.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset