Generative Adversarial Training for Neural Machine Translation
Yang Z(杨振); Chen W(陈炜); Wang F(王峰)
2018
发表期刊NeuroComputing
期号100页码:1-10
摘要
; Neural machine translation (NMT) is typically optimized to generate sentences which cover n-grams with ground target as much as possible. However, it is widely acknowledged that n-gram precisions, the manually designed approximate loss function, may mislead the model to generate suboptimal translations. To solve this problem, we train the NMT model to generate human-like translations directly by using the generative adversarial net, which has achieved great success in computer vision. In this paper, we build a conditional sequence generative adversarial net (CSGAN-NMT) which comprises of two adversarial sub models, a generative model (generator) which translates the source sentence into the target sentence as the traditional NMT models do and a discriminative model (discriminator) which discriminates the machine-translated target sentence from the human-translated one. The two sub models play a minimax game and achieve a win-win situation when reaching a Nash Equilibrium. As a variant of the single generator-discriminator model, the multi-CSGAN-NMT which contains multiple discriminators and generators, is also proposed. In the multi-CSGAN-NMT model, each generator is viewed as an agent which can interact with others and even transfer messages. Experiments show that the proposed CSGAN-NMT model obtains substantial improvements than the strong baseline and the improvement of the multi-CSGAN-NMT model is more remarkable.
关键词Neural Machine Translation
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/22087
专题数字内容技术与服务研究中心_听觉模型与认知计算
推荐引用方式
GB/T 7714
Yang Z,Chen W,Wang F. Generative Adversarial Training for Neural Machine Translation[J]. NeuroComputing,2018(100):1-10.
APA Yang Z,Chen W,&Wang F.(2018).Generative Adversarial Training for Neural Machine Translation.NeuroComputing(100),1-10.
MLA Yang Z,et al."Generative Adversarial Training for Neural Machine Translation".NeuroComputing .100(2018):1-10.
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
csganpr.pdf(682KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yang Z(杨振)]的文章
[Chen W(陈炜)]的文章
[Wang F(王峰)]的文章
百度学术
百度学术中相似的文章
[Yang Z(杨振)]的文章
[Chen W(陈炜)]的文章
[Wang F(王峰)]的文章
必应学术
必应学术中相似的文章
[Yang Z(杨振)]的文章
[Chen W(陈炜)]的文章
[Wang F(王峰)]的文章
相关权益政策
暂无数据
收藏/分享
文件名: csganpr.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。