Synchronously Generating Two Languages with Interactive Decoding

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 自然语言处理

	Synchronously Generating Two Languages with Interactive Decoding
	Wang,Yining1,2 ; Zhang,Jiajun1,2 ; Zhou,Long1,2 ; Liu,Yuchen1,2 ; Zong,Chengqing1,2,3
	2019-11
会议名称	Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing
会议日期	November 3–7, 2019
会议地点	Hong Kong, China
摘要	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.
收录类别	EI
语种	英语
七大方向——子方向分类	自然语言处理
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/39235
专题	多模态人工智能系统全国重点实验室_自然语言处理
通讯作者	Zhang,Jiajun
作者单位	1.National Laboratory of Pattern Recognition, CASIA, Beijing, China 2.University of Chinese Academy of Sciences, Beijing, China 3.CAS Center for Excellence in Brain Science and Intelligence Technology, Beijing, China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wang,Yining,Zhang,Jiajun,Zhou,Long,et al. Synchronously Generating Two Languages with Interactive Decoding[C],2019.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Synchronously Genera（679KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载