[1]赵 阳,周 龙,王 迁,等.民汉稀缺资源神经机器翻译技术研究[J].江西师范大学学报(自然科学版),2019,(06):630-637.[doi:10.16357/j.cnki.issn1000-5862.2019.06.12]
 ZHAO Yang,ZHOU Long,WANG Qian,et al.The Study on Ethnic-to-Chinese Scare-Resource Neural Machine Translation[J].Journal of Jiangxi Normal University:Natural Science Edition,2019,(06):630-637.[doi:10.16357/j.cnki.issn1000-5862.2019.06.12]
点击复制

民汉稀缺资源神经机器翻译技术研究()
分享到:

《江西师范大学学报》(自然科学版)[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年06期
页码:
630-637
栏目:
机器翻译
出版日期:
2019-12-10

文章信息/Info

Title:
The Study on Ethnic-to-Chinese Scare-Resource Neural Machine Translation
文章编号:
1000-5862(2019)06-0630-08
作者:
赵 阳周 龙王 迁马 聪刘宇宸王亦宁向 露张家俊周 玉宗成庆
中国科学院自动化研究所,北京 100190
Author(s):
ZHAO YangZHOU LongWANG QianMA CongLIU YuchenWANG YiningXIANG LuZHANG JiajunZHOU YuZONG Chengqing
Institute of Automation,Chinese Academy of Science,Beijing 100190,China
关键词:
神经机器翻译 低资源翻译 自注意力机制
Keywords:
neural machine translation low-resource machine translation self-attention mechanism
分类号:
TP 302.1
DOI:
10.16357/j.cnki.issn1000-5862.2019.06.12
文献标志码:
A
摘要:
该文介绍了中国科学院自动化研究所参加第15届全国机器翻译大会(CCMT2019)翻译评测任务总体情况以及采用的技术细节.在评测中,中国科学院自动化研究所参加了3个翻译任务,分别是蒙汉日常用语机器翻译、藏汉政府文献机器翻译以及维汉新闻领域机器翻译; 阐述了参评系统采用的模型框架、数据预处理方法以及译码策略; 最后给出了不同设置下评测系统在测试数据集上的表现,并进行了对比和分析.
Abstract:
The overview and the technical details adopted by Institute of Automation Chinese Academy of Science(CASIA)to participate in the 15th China Conference on Machine Translation(CCMT 2019)evaluation tasks are described in the paper.In the conference,CASIA participates in three translation tasks,including Mongolian-Chinese daily language machine translation,Tibetan-Chinese government literature machine translation,and Uyghur-Chinese news machine translation.The content of the report describes the model framework,datasets pre-processing methods and decoding strategies.Lastly,the report gives the performance of the system on the evaluation dataset under different settings and conducts a comparative analysis.

参考文献/References:

[1] Vaswani A,Shazeer N,Parmar N,et al.Attention is all you need[EB/OL].[2019-04-17].https://arxiv.org/abs/1706.03762.
[2] Sennrich R,Haddow B,Birch A.Neural machine translation of rare words with subwordunits[EB/OL].[2019-04-17].https://arxiv.org/abs/1508.07909.
[3] 刘宇宸,闫璟辉,张家俊,等.第14届机器翻译研讨会中科院自动化所技术报告[EB/OL].[2019-04-17].https://max.book118.com/html/2019/0123/6152242142002003.shtm.
[4] Cho K,Gulcehre B V M C,Bahdanau D,et al.Learning phrase representationsusing rnn encoder-decoder for statistical machine translation[EB/OL].[2019-04-17].https://arxiv.org/abs/1406.1078.
[5] Gehring J,Auli M,Grangier D,et al.Convolutional sequence to sequence learning[EB/OL].[2019-04-17].https://arxiv.org/pdf/1705.03122.pdf.
[6] Hinton G,Vinyals O,Dean J.Distilling the knowledge in a neural network[EB/OL].[2019-04-17].https://arxiv.org/abs/1503.02531.
[7] Dyer C,Chahuneau V,Smith N A.A simple,fast,and effective Reparameterization of IBM Model 2[EB/OL].[2019-04-17].https://www.aclweb.org/anthology/N13-1073.
[8] Stolcke A.SRILM:an extensible language modeling toolkit[EB/OL].[2019-04-17].https://www.bibsonomy.org/bibtex/3c28bc012b07b969bbd7df72f7e19762.
[9] Edunov S,Ott M,Auli M,et al.Understandingback-translation at scale[EB/OL].[2019-04-17].https://arxiv.org/abs/1808.09381.
[10] Sennrich R,Birch A,Currey A,et al.The university of edinburgh'sneural MT systems for WMT17[EB/OL].[2019-04-17].https://arxiv.org/pdf/1708.00726.pdf.
[11] Liu Yuchen,Zhou Long,Wang Yining,et al.A comparable study on model averaging,ensembling and reranking in nmt[EB/OL][2019-04-17].http://link.springer.com/chapter/10.1007/978-3-319-99501-4_26.
[12] Liu Lemao,Utiyama M,Finch A,et al.Agreement on target-bidirectional neural machine translation[EB/OL].[2019-04-17].https://www.researchgate.net/publication/305334571_Agreement_on_Target-bidirectional_Neural_Machine_Translation.
[13] Zhao Yang,Zhang Jiajun,He Zhongjun,et al.Addressing troublesome words in neural machine translation[EB/OL].[2019-04-12].∥https://www.researchgate.net/publication/334116501_Addressing_Troublesome_Words_in_Neural_Machine_Translation.
[14] Zhou Long,Zhang Jiajun,Zong Chengqing.Synchronous bidirectional neural machine translation[J].Transactions of the Association for Computational Linguistics,2019,7:91-105.
[15] Shu R,Nakayama H.Later-stage minimum Bayes-risk decoding for neural machine translation[EB/OL].[2019-04-17].https://arxiv.org/pdf/1704.03169.pdf.
[16] Omar F Zaidan.Z-MERT:a fully configurable open source tool for minimum error rate training of machine translation systems[J].The Prague Bulletin of Mathematical Linguistics,2009,91:79-88.

相似文献/References:

[1]王 坤,殷明明,俞鸿飞,等.低资源维汉神经机器翻译研究[J].江西师范大学学报(自然科学版),2019,(06):638.[doi:10.16357/j.cnki.issn1000-5862.2019.06.13]
 WANG Kun,YIN Mingming,YU Hongfei,et al.The Study on Low-Resource Uygur-Chinese Neural Machine Translation[J].Journal of Jiangxi Normal University:Natural Science Edition,2019,(06):638.[doi:10.16357/j.cnki.issn1000-5862.2019.06.13]
[2]谷舒豪,单 勇,谢婉莹,等.基于数据增强及领域适应的神经机器翻译技术[J].江西师范大学学报(自然科学版),2019,(06):643.[doi:10.16357/j.cnki.issn1000-5862.2019.06.14]
 GU Shuhao,SHAN Yong,XIE Wanying,et al.The Neural Machine Translation Based on Data Augmentation and Domain Adaptation Technology[J].Journal of Jiangxi Normal University:Natural Science Edition,2019,(06):643.[doi:10.16357/j.cnki.issn1000-5862.2019.06.14]
[3]刘俊鹏,宋鼎新,张一鸣,等.多种数据泛化策略融合的神经机器翻译系统[J].江西师范大学学报(自然科学版),2020,(01):39.[doi:10.16357/j.cnki.issn1000-5862.2020.01.07]
 LIU Junpeng,SONG Dingxin,ZHANG Yiming,et al.The Neural Machine Translation System of Multiple Data Generalization Fusion[J].Journal of Jiangxi Normal University:Natural Science Edition,2020,(06):39.[doi:10.16357/j.cnki.issn1000-5862.2020.01.07]

备注/Memo

备注/Memo:
收稿日期:2019-09-07
基金项目:国家重点研发计划(2016QY02D0303),国家自然科学基金(U1836221)和北京市科技计划(Z181100008918017)资助项目.
作者简介:赵 阳(1990-),男,山西运城人,助理研究员,博士,主要从事机器翻译、自然语言处理研究.E-mail:yang.zhao@nlpr.ia.ac.cn
更新日期/Last Update: 2019-12-10