Synchronously Generating Two Languages with Interactive Decoding

Synchronously Generating Two Languages with Interactive Decoding
复制标题

DOI:
10.18653/v1/d19-1330
复制
发表时间:
2019-11
期刊:
--
影响因子:
--
通讯作者:
Yining Wang;Jiajun Zhang;Long Zhou;Yuchen Liu-;Chengqing Zong
Yining Wang;Jiajun Zhang;Long Zhou;Yuchen Liu-;Chengqing Zong
中科院分区:
其他
文献类型:
--
作者:
Yining Wang;Jiajun Zhang;Long Zhou;Yuchen Liu-;Chengqing Zong

文献摘要

被引文献

相似文献

在本文中,我们介绍了一种新颖的交互式方法,可以将源语言同时交互式地翻译成两种不同的语言。具体来说,一种语言的生成不仅依赖于其本身先前生成的输出,还依赖于另一种语言预测的输出。 IWSLT 和 WMT 数据集上的实验结果表明,我们的方法比传统的神经机器翻译(NMT)模型和多语言 NMT 模型都获得了显着的改进。
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.