Reference Network for Neural Machine Translation

被引:0
|
作者
Fu, Han [1 ,2 ]
Liu, Chenghao [3 ]
Sun, Jianling [1 ,2 ]
机构
[1] Zhejiang Univ, Hangzhou, Zhejiang, Peoples R China
[2] Alibaba Zhejiang Univ Joint Inst Frontier Technol, Hangzhou, Zhejiang, Peoples R China
[3] Singapore Management Univ, Singapore, Singapore
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Neural Machine Translation (NMT) has achieved notable success in recent years. Such a framework usually generates translations in isolation. In contrast, human translators often refer to reference data, either rephrasing the intricate sentence fragments with common terms in source language, or just accessing to the golden translation directly. In this paper, we propose a Reference Network to incorporate referring process into translation decoding of NMT. To construct a reference book, an intuitive way is to store the detailed translation history with extra memory, which is computationally expensive. Instead, we employ Local Coordinates Coding (LCC) to obtain global context vectors containing monolingual and bilingual contextual information for NMT decoding. Experimental results on Chinese-English and English-German tasks demonstrate that our proposed model is effective in improving the translation quality with lightweight computation cost.
引用
收藏
页码:3002 / 3012
页数:11
相关论文
共 50 条
  • [1] Reference Language based Unsupervised Neural Machine Translation
    Li, Zuchao
    Zhao, Hai
    Wang, Rui
    Utiyama, Masao
    Sumita, Eiichiro
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 4151 - 4162
  • [2] Detecting Failures of Neural Machine Translation in the Absence of Reference Translations
    Wang, Wenyu
    Zheng, Wujie
    Liu, Dian
    Zhang, Changrong
    Zeng, Qinsong
    Deng, Yuetang
    Yang, Wei
    He, Pinjia
    Xie, Tao
    [J]. 49TH ANNUAL IEEE/IFIP INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS AND NETWORKS (DSN 2019): INDUSTRY TRACK, 2019, : 1 - 4
  • [3] Research on Machine Translation Model Based on Neural Network
    Han, Zhuoran
    Li, Shenghong
    [J]. COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, CSPS 2018, VOL III: SYSTEMS, 2020, 517 : 244 - 251
  • [4] A Recursive Recurrent Neural Network for Statistical Machine Translation
    Liu, Shujie
    Yang, Nan
    Li, Mu
    Zhou, Ming
    [J]. PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2014, : 1491 - 1500
  • [5] Machine Translation based on Neural Network Language Models
    Zamora-Martinez, Francisco
    Jose Castro-Bleda, Maria
    [J]. PROCESAMIENTO DEL LENGUAJE NATURAL, 2010, (45): : 221 - 228
  • [6] Opportunities and Implementation of Neural Machine Translation for Network Configuration
    Li, Fuliang
    Zhang, Jiajie
    Li, Minglong
    Wang, Xingwei
    [J]. IEEE NETWORK, 2023, 37 (04): : 82 - 89
  • [7] A Unified Neural Network for Quality Estimation of Machine Translation
    Li, Maoxi
    Xiang, Qingyu
    Chen, Zhiming
    Wang, Mingwen
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2018, E101D (09): : 2417 - 2421
  • [8] MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation
    Mahata, Sainik Kumar
    Das, Dipankar
    Bandyopadhyay, Sivaji
    [J]. JOURNAL OF INTELLIGENT SYSTEMS, 2019, 28 (03) : 447 - 453
  • [9] Recurrent Neural Network Techniques: Emphasis on Use in Neural Machine Translation
    Suleiman, Dima
    Etaiwi, Wael
    Awajan, Arafat
    [J]. INFORMATICA-AN INTERNATIONAL JOURNAL OF COMPUTING AND INFORMATICS, 2021, 45 (07): : 107 - 114
  • [10] Differentiable Sampling with Flexible Reference Word Order for Neural Machine Translation
    Xu, Weijia
    Niu, Xing
    Carpuat, Marine
    [J]. 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 2047 - 2053