Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Pair
This work addresses machine translation for a low-resource language pair, which is incremental as it applies existing techniques to a new dataset.
The paper tackled the problem of low-resource neural machine translation for the Russian-Tatar language pair, achieving improvements of +2.57 BLEU for Russian to Tatar and +3.66 BLEU for Tatar to Russian by applying techniques like transfer learning and semi-supervised learning to a Transformer model.
Neural machine translation is the current state-of-the-art in machine translation. Although it is successful in a resource-rich setting, its applicability for low-resource language pairs is still debatable. In this paper, we explore the effect of different techniques to improve machine translation quality when a parallel corpus is as small as 324 000 sentences, taking as an example previously unexplored Russian-Tatar language pair. We apply such techniques as transfer learning and semi-supervised learning to the base Transformer model, and empirically show that the resulting models improve Russian to Tatar and Tatar to Russian translation quality by +2.57 and +3.66 BLEU, respectively.