Exploiting Japanese-Chinese Cognates with Shared Private Representations for NMT.

Neural machine translation (NMT) has achieved remarkable progress in the past several years; however, little attention has been paid to MT between Japanese and Chinese who share a large proportion of cognate words that can be utilized as additional linguistic knowledge to enhance translation performance. In this article, we seek to strengthen the semantic correlation between Japanese and Chinese by leveraging cognate words that share common Chinese characters. Specifically, we experiment with three strategies: (1) a shared vocabulary with cognate lexicon induction, which models the commonality between source and target cognates; (2) a shared private representation with a dynamic gating mechanism, which models the language-specific features on the source side; and (3) an embedding shortcut, which enables the decoder to access the shared private representation with shortest distance and aids the training process. The experiments and analysis presented in this paper demonstrate that our proposed approaches can significantly improve the performance of both Japanese-to-Chinese and Chinese-to-Japanese translations and verify the effectiveness of exploiting Japanese-Chinese cognates for MT.