Improved English to Russian Translation by Neural Suffix Prediction


  • Kai Song Soochow University, Alibaba Group
  • Yue Zhang Singapore University of Technology and Design
  • Min Zhang Soochow University
  • Weihua Luo Alibaba Group



morphology, Russain, machine translation


Neural machine translation (NMT) suffers a performance deficiency when a limited vocabulary fails to cover the source or target side adequately, which happens frequently when dealing with morphologically rich languages. To address this problem, previous work focused on adjusting translation granularity or expanding the vocabulary size. However, morphological information is relatively under-considered in NMT architectures, which may further improve translation quality. We propose a novel method, which can not only reduce data sparsity but also model morphology through a simple but effective mechanism. By predicting the stem and suffix separately during decoding, our system achieves an improvement of up to 1.98 BLEU compared with previous work on English to Russian translation. Our method is orthogonal to different NMT architectures and stably gains improvements on various domains.




How to Cite

Song, K., Zhang, Y., Zhang, M., & Luo, W. (2018). Improved English to Russian Translation by Neural Suffix Prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).