While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. In this paper, we propose a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language. Based on this assumption, our method is able to train a source-to-target NMT model ("student") without parallel corpora available, guided by an existing pivot-to-target NMT model ("teacher") on a source-pivot parallel corpus. Experimental results show that the proposed method significantly improves over a baseline pivot-based model by +3.0 BLEU points across various language pairs.
@article{arxiv.1705.00753,
title = {A Teacher-Student Framework for Zero-Resource Neural Machine Translation},
author = {Yun Chen and Yang Liu and Yong Cheng and Victor O. K. Li},
journal= {arXiv preprint arXiv:1705.00753},
year = {2017}
}