Abstract
In this paper, we introduce a novel interactive approach to translate a source language into two different languages simultaneously and interactively. Specifically, the generation of one language relies on not only previously generated outputs by itself, but also the outputs predicted in the other language. Experimental results on IWSLT and WMT datasets demonstrate that our method can obtain significant improvements over both conventional Neural Machine Translation (NMT) model and multilingual NMT model.
Cite
CITATION STYLE
Wang, Y., Zhang, J., Zhou, L., Liu, Y., & Zong, C. (2019). Synchronously generating two languages with interactive decoding. In EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Proceedings of the Conference (pp. 3350–3355). Association for Computational Linguistics. https://doi.org/10.18653/v1/d19-1330
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
