Effective Strategies in Zero-Shot Neural Machine Translation

11/21/2017

∙

by   Thanh-Le Ha, et al.

∙

0

∙

share

In this paper, we proposed two strategies which can be applied to a multilingual neural machine translation system in order to better tackle zero-shot scenarios despite not having any parallel corpus. The experiments show that they are effective in terms of both performance and computing resources, especially in multilingual translation of unbalanced data in real zero-resourced condition when they alleviate the language bias problem.