Zero-Resource Translation with Multi-Lingual Neural Machine Translation

Abstract

In this paper, we propose a novel finetuning algorithm for the recently introduced multiway, multilingual neural machine translate that enables zero-resource machine translation. When used together with novel manyto-one translation strategies, we empirically show that this finetuning algorithm allows the multi-way, multilingual model to translate a zero-resource language pair (1) as well as a single-pair neural translation model trained with up to 1M direct parallel sentences of the same language pair and (2) better than pivotbased translation strategy, while keeping only one additional copy of attention-related parameters.