Finding Better Subwords for Tibetan Neural Machine Translation

Abstract

Subword segmentation plays an important role in Tibetan neural machine translation (NMT). The structure of Tibetan words consists of two levels. First, words consist of a sequence of syllables, and then a syllable consists of a sequence of characters. According to this special word structure, we propose two methods for Tibetan subword segmentation, namely syllable-based and character-based methods. The former generates subwords based on the Tibetan syllables, and the latter is based on Tibetan characters. In addition, we carry out experiments with these two subword segmentation methods on low-resource Tibetan-to-Chinese NMT, respectively. The experimental results show that both of them can improve translation performance, in which the subword segmentation based on character sequences can achieve better results. Overall, our proposed character-based subword segmentation is more simple and effective. Moreover, it can achieve better experimental results without paying much attention to the linguistic features of Tibetan.