|本期目录/Table of Contents|

[1]张 巍*,林飞飞,梁镇爽,等.一种可扩展的深度神经网络机器翻译Service架构[J].厦门大学学报(自然科学版),2019,58(02):184-188.[doi:10.6043/j.issn.0438-0479.201811006]
 ZHANG Wei*,LIN Feifei,LIANG Zhenshuang,et al.A scalable deep neural network machine translation service[J].Journal of Xiamen University(Natural Science),2019,58(02):184-188.[doi:10.6043/j.issn.0438-0479.201811006]
点击复制

一种可扩展的深度神经网络机器翻译Service架构(PDF/HTML)
分享到:

《厦门大学学报(自然科学版)》[ISSN:0438-0479/CN:35-1070/N]

卷:
58卷
期数:
2019年02期
页码:
184-188
栏目:
机器翻译模型
出版日期:
2019-03-27

文章信息/Info

Title:
A scalable deep neural network machine translation service
文章编号:
0438-0479(2019)02-0184-05
作者:
张 巍1*林飞飞1梁镇爽2黄 振2
1.中国海洋大学信息科学与工程学院,山东 青岛 266100; 2.中译语通信息科技(青岛)有限公司,山东 青岛 266061
Author(s):
ZHANG Wei1*LIN Feifei1LIANG Zhenshuang2HUANG Zhen2
College of Information Science and Engineering,Ocean University of China,Qingdao 266100,China; Global Tone Communication Technology(Qingdao)Co.,Ltd.,Qingdao 266061,China
关键词:
神经机器翻译 在线翻译 混合解码
Keywords:
neural machine translation service online translation hybrid decoding
分类号:
TP 391
DOI:
10.6043/j.issn.0438-0479.201811006
文献标志码:
A
摘要:
提出了一种可扩展的基于深度神经网络方法的在线翻译系统架构方法,采用GPU和CPU混合解码的后端部署方法来提高系统的并发能力,降低系统延迟.实验结果表明,所提出的系统架构方法相比于只使用GPU或CPU架构,系统并发能力更强,而响应延迟相对较低.同时系统的架构方法可以方便地扩展到多服务器架构中,整体上提高系统的性能.
Abstract:
Neural network machine translation,which is a new machine translation method,has become the mainstream of machine translation research.In this paper,we propose an extensible online translation system architecture based on deep neural network,which builds the system backend through the method of GPU and CPU mixed decoding to improve the concurrency ability of the system,and reduce system delay.Experimental results show that the proposed system architecture method is effective.Compared to pure GPU or CPU architecture,the system has higher concurrency ability and the response delay is relatively low.At the same time,the architecture can be extended to the multi-server architecture and improve the performance of the system further.

参考文献/References:

[1] SUTSKEVER I,VINYALS O,LE Q.Sequence to sequence learning with neural networks[C] ∥Proc of the 28th NIPS.New York:Curran Associates Inc,2014:3104-3112.
[2] BROWN P,DELLA PIETRA S,DELLA PIETRA V,et al.The mathematics of statistical machine translation:Parameter estimation[J].Computational Linguistics,1993,19(2):263-311.
[3] CHIANG D.A hierarchical phrase-based model for statistical machine translation[C] ∥Proc of the 43rd ACL.Stroudsburg:ACL,2005:263-270.
[4] OCH F J,MARCU D.Statistical phrase-based translation[C]∥HLT-NAACL.New York:ACM,2003:48-54.
[5] 刘洋.基于深度学习的机器翻译研究进展[J].中国人工智能学会通讯,2015(10):28-32.
[6] 王海峰,吴华,刘占一.互联网机器翻译[J].中文信息学报,2011,25(6):72-80.
[7] 庞斌.机器翻译——从统计学方法到神经网络[J].研究与探讨,2016(12):296-297.
[8] BAHDANAU D,CHO K,BENGIO Y.Neural machine translation by jointly learning to align and translate[EB/OL].[2018-10-01].https:∥arxiv.org/abs/1409.0473.
[9] GRAVES A.Long short-term memory[M]∥Supervised sequence labelling with recurrent neural networks.Berlin Heidelberg:Springer,2012:1735-1780.
[10] JUNCZYS-DOWMUNT M,DWOJAK T,HOANG H.Is neural machine translation ready for deployment? A case study on 30 translation directions[EB/OL].[2018-10-01].https:∥arxiv.org/abs/1610.01108v2.
[11] LUONG T,PHAM H,MANNING C D.Effective approaches to attention-based neural machine translation∥Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.Lisbon:[s.n.],2015:1412-1421.
[12] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[13] 刘洋.神经机器翻译前沿进展[J].计算机研究与发展,2017,54(6):1144-1149.[1] SUTSKEVER I,VINYALS O,LE Q.Sequence to sequence learning with neural networks[C] ∥Proc of the 28th NIPS.New York:Curran Associates Inc,2014:3104-3112.
[2] BROWN P,DELLA PIETRA S,DELLA PIETRA V,et al.The mathematics of statistical machine translation:Parameter estimation[J].Computational Linguistics,1993,19(2):263-311.
[3] CHIANG D.A hierarchical phrase-based model for statistical machine translation[C] ∥Proc of the 43rd ACL.Stroudsburg:ACL,2005:263-270.
[4] OCH F J,MARCU D.Statistical phrase-based translation[C]∥HLT-NAACL.New York:ACM,2003:48-54.
[5] 刘洋.基于深度学习的机器翻译研究进展[J].中国人工智能学会通讯,2015(10):28-32.
[6] 王海峰,吴华,刘占一.互联网机器翻译[J].中文信息学报,2011,25(6):72-80.
[7] 庞斌.机器翻译——从统计学方法到神经网络[J].研究与探讨,2016(12):296-297.
[8] BAHDANAU D,CHO K,BENGIO Y.Neural machine translation by jointly learning to align and translate[EB/OL].[2018-10-01].https:∥arxiv.org/abs/1409.0473.
[9] GRAVES A.Long short-term memory[M]∥Supervised sequence labelling with recurrent neural networks.Berlin Heidelberg:Springer,2012:1735-1780.
[10] JUNCZYS-DOWMUNT M,DWOJAK T,HOANG H.Is neural machine translation ready for deployment? A case study on 30 translation directions[EB/OL].[2018-10-01].https:∥arxiv.org/abs/1610.01108v2.
[11] LUONG T,PHAM H,MANNING C D.Effective approaches to attention-based neural machine translation∥Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.Lisbon:[s.n.],2015:1412-1421.
[12] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[13] 刘洋.神经机器翻译前沿进展[J].计算机研究与发展,2017,54(6):1144-1149.

备注/Memo

备注/Memo:
收稿日期:2018-11-05 录用日期:2019-01-10
*通信作者:weizhang@ouc.edu.cn
更新日期/Last Update: 1900-01-01