CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Generative adversarial training for neural machine translation
Yang Z(杨振); Chen W(陈炜); Wang F(王峰)
Source PublicationNEUROCOMPUTING
ISSN0925-2312
2018-12-10
Volume321Issue:333Pages:146-155
Contribution Rank1
Abstract

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 mini max 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. (C) 2018 Elsevier B.V. All rights reserved.

KeywordNeural machine translation Multi generative adversarial net Human-like translation
DOI10.1016/j.neucom.2018.09.006
Indexed BySCI
Language英语
Funding ProjectNational Program on Key Basic Research Project of China (973 Program)[2013CB329302]
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000447385100014
PublisherELSEVIER SCIENCE BV
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/22087
Collection数字内容技术与服务研究中心_听觉模型与认知计算
Affiliation中国科学院自动化研究所
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Yang Z,Chen W,Wang F. Generative adversarial training for neural machine translation[J]. NEUROCOMPUTING,2018,321(333):146-155.
APA Yang Z,Chen W,&Wang F.(2018).Generative adversarial training for neural machine translation.NEUROCOMPUTING,321(333),146-155.
MLA Yang Z,et al."Generative adversarial training for neural machine translation".NEUROCOMPUTING 321.333(2018):146-155.
Files in This Item: Download All
File Name/Size DocType Version Access License
csganpr.pdf(682KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang Z(杨振)]'s Articles
[Chen W(陈炜)]'s Articles
[Wang F(王峰)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang Z(杨振)]'s Articles
[Chen W(陈炜)]'s Articles
[Wang F(王峰)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang Z(杨振)]'s Articles
[Chen W(陈炜)]'s Articles
[Wang F(王峰)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: csganpr.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.