Addressing Syntactic Divergence in Low-Resource Neural Machine Translation via Language Independent Word Reordering

Neural machine translation using the combination of parallel and synthetic corpus has achieved impressive translation performance for several language pairs, where the synthetic corpus is typically generated by back-translating the monolingual target sentences. However, the quality of the synthetic corpus is poor in low-resource scenarios, which reduces the contribution of data augmentation methods such as back translation to the translation quality, especially for syntactically distant language pairs. In this paper, we propose a novel solution which uses a language independent word reordering method to address syntactic divergences between the target and source languages. The method indirectly converts the word order of the target language to the source language using an assisting language that has a similar word order to the source language and has sufficient sentence pairs with the target language. A higher quality synthetic corpus can be obtained by translating source-ordered monolingual target sentences using a bilingual dictionary. The synthetic corpus and the parallel corpus are merged to train a more powerful NMT model. Experiments on real low-resource Tibetan-Chinese, Uyghur-Chinese and Mongolian-Chinese show that our method achieves significant improvements over other semi-supervised methods. Our word reordering method avoids problems such as insufficient reordering training data and immature lexical analysers.