|本期目录/Table of Contents|

[1]谭 敏,殷明明,段湘煜*.神经机器翻译的系统融合方法[J].厦门大学学报(自然科学版),2019,58(04):600-607.[doi:10.6043/j.issn.0438-0479.201903015]
 TAN Min,YIN Mingming,DUAN Xiangyu*.System combination method for neural machine translation[J].Journal of Xiamen University(Natural Science),2019,58(04):600-607.[doi:10.6043/j.issn.0438-0479.201903015]
点击复制

神经机器翻译的系统融合方法(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04期
页码:
600-607
栏目:
研究论文
出版日期:
2019-07-28

文章信息/Info

Title:
System combination method for neural machine translation
文章编号:
0438-0479(2019)04-0600-08
作者:
谭 敏殷明明段湘煜*
苏州大学计算机科学与技术学院,江苏 苏州 215006
Author(s):
TAN MinYIN MingmingDUAN Xiangyu*
School of Computer Science and Technology,Soochow University,Suzhou 215006,China
关键词:
神经机器翻译 循环神经网络 系统融合 注意力机制 门机制
Keywords:
neural machine translation recurrent neural network system combination attention mechanism gate mechanism
分类号:
TP 391.2
DOI:
10.6043/j.issn.0438-0479.201903015
文献标志码:
A
摘要:
为了提高机器翻译模型的泛化能力,基于神经机器翻译系统,将系统融合技术应用于模型训练过程.在神经机器翻译系统的基本结构——编码器-解码器结构的基础上,提出5种融合方法(平均融合、权重融合、拼接融合、门机制融合和注意力机制融合)分别应用于多个编码器-一个解码器的融合、多个编码器-多个解码器的融合和一个编码器-多个解码器的融合.在中英翻译任务上进行实验,相对于基准系统,系统融合方法改进的机器翻译模型的机器双语互译评估(BLEU)值最终提升了0.59~3.01个百分点.实验结果表明,系统融合能有效地提升译文质量.
Abstract:
To improve the generalization ability of the machine translation model, we have applied the system combination technology to the model training process based on the neural machine translation system.According to the encoder-decoder structure of the neural machine translation system, five combination methods are proposed,including average combination,weight combination, concatenation combination, gate mechanism combination and attention mechanism combination.They are applied to the combination of multiple encoders and one decoder,the combination of multiple encoders and multiple decoders and the combination of one encoder and multiple decoders,respectively.Subsequently,the method is applied to the Chinese-English translation task.Compared with the benchmark system,the BLEU value of the machine translation model improved by the system combination method is finally increased by 0.59-3.01 percentage point.Experimental results show that the system combination can effectively improve the translation quality.

参考文献/References:

[1] OCH F J,NEY H.Statistical multi-source translation.[C]∥MT Summit 2001.Santiago de Compostela:Proceedings of MT Summit,2001:253-258.
[2] MATUSOV E,UEFFING N,NEY H.Computing consensus translation for multiple machine translation systems using enhanced hypothesis alignment[C]∥11th Conference of the European Chapter of the Association for Computa-tional Linguistics,Proceedings of the Conference.Trento:ACL,2006:33-40.
[3] SCHWARTZ L.Multi-source translation methods[C]∥8th Conference of the Association for Machine Translation Proceedings of AMTA.Hawaii:AMTA,2008:279-288.
[4] 李茂西,宗成庆.机器翻译系统融合技术综述[J].中文信息学报,2010,24(4):74-85.
[5] SUTSKEVER I,VINYALS O,LEQ V.Sequence to sequen-ce learning with neural networks[C]∥Proceedings of Adva-nces in neural information processing systems.Montreal:NIPS,2014:3104-3112.
[6] BAHDANAUD,CHO K,BENGIO Y.Neural machine translation by jointly learning to align and translate[EB/OL].[2019-03-05].https:∥arxiv.org/pdf/1409.0472.pdf.
[7] LUONG M T,PHAM H,MANNING C D.Effective approaches to attention-based neural machine translation[C]∥Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.Lisbon:ACL,2015:1412-1421.
[8] DIETTERICH T G.Ensemble methods in machine learn-ing[C]∥Proceedings of International workshop on multiple classifier systems.Berlin:Springer,2000:1-15.
[9] ZOPH B,KNIGHT K.Multi-source neural translation[C]∥The 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.San Diego California:ACL,2016:30-34.
[10] FIRAT O,SANKARANB,AL-ONAIZAN Y,et al.Zero-resource translation with multi-lingualneural machine transla-tion[EB/OL].[2019-03-05]. https:∥arxiv.org/pdf/1606.04164.pdf.
[11] GARMASH E,MONZ C.Ensemble learning for multi-source neural machine translation[C]∥Proceedings of the 26th International Conference on Computational Linguis-tics.Osaka:ACL,2016:1409-1418.
[12] ZHOU L,HU W,ZHANG J,et al.Neural system combi-nation for machine translation[C]∥Proceedings of the 55th Annual Meeting of the Association for Computa-tional Linguistics.Vancouver:ACL,2017:378-384.
[13] CHO K,VAN MERRI?NBOER B,GULCEHRE C,et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]∥Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing.Doha:ACL,2014:1724-1734.
[14] HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[15] HANSEN L K,SALAMON P.Neural network ensembles[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1990,12(10):993-1001.
[16] PAPINENI K,ROUKOS S,WARD T,et al.BLEU:a method for automatic evaluation of machine translation[C]∥Proceedings of the 40th Annual Meeting on Association for Computational Linguistics.Philadelphia:ACL,2002:311-318.
[17] JEAN S,CHO K,MEMISEVIC R,et al.On using very large target vocabulary for neural machine translation[C]∥ Proceedings of the 53th Annual Meeting of the Association for Comutational Linguistics.Beijing:ACL,2015:1-10.
[18] GEHRING J,AULI M,GRANGIER D,et al.Convolu-tional sequence to sequence learning[C]∥Proceedings of the 34th International Conference on Machine Learning.Sydney:PMLR,2017:1243-1252.
[19] VASWANI A,SHAZEER N,PARMAR N,et al.Atten-tion is all you need[C]∥Advances in Neural Informa-tion Processing Systems.Long Beach:NIPS,2017:5998-6008.

备注/Memo

备注/Memo:
收稿日期:2019-03-08录用日期:2019-05-04
基金项目:国家重点研发计划(2016YFE0132100); 国家自然科学基金(61673289)
*通信作者:xiangyuduan@suda.edu.cu
更新日期/Last Update: 1900-01-01