Multi-way, multilingual neural machine translation

被引:40
|
作者
Firat, Orhan [1 ]
Cho, Kyunghyun [2 ]
Sankaran, Baskaran [3 ]
Vural, Fatos T. Yarman [1 ]
Bengio, Yoshua [4 ]
机构
[1] Middle East Tech Univ, Ankara, Turkey
[2] NYU, New York, NY 10003 USA
[3] IBM TJ Watson Res Ctr, Cambridge, MA USA
[4] Univ Montreal, Montreal, PQ, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Neural machine translation; Multi-lingual; Low resource translation;
D O I
10.1016/j.csl.2016.10.006
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is shared across all language pairs. We train the proposed multi-way, multilingual model on ten language pairs from WMT'15 simultaneously and observe clear performance improvements over models trained on only one language pair. We empirically evaluate the proposed model on low-resource language translation tasks. In particular, we observe that the proposed multilingual model outperforms strong conventional statistical machine translation systems on Turkish-English and Uzbek-English by incorporating the resources of other language pairs. (C) 2016 Elsevier Ltd. All rights reserved
引用
收藏
页码:236 / 252
页数:17
相关论文
共 50 条
  • [21] Multi-Source Neural Model for Machine Translation of Agglutinative Language
    Pan, Yirong
    Li, Xiao
    Yang, Yating
    Dong, Rui
    FUTURE INTERNET, 2020, 12 (06):
  • [22] Multi-Teacher Distillation With Single Model for Neural Machine Translation
    Liang, Xiaobo
    Wu, Lijun
    Li, Juntao
    Qin, Tao
    Zhang, Min
    Liu, Tie-Yan
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2022, 30 : 992 - 1002
  • [23] Risks in neural machine translation
    Canfora, Carmen
    Ottmann, Angelika
    TRANSLATION SPACES, 2020, 9 (01) : 58 - 77
  • [24] A Survey of Neural Machine Translation
    Li Y.-C.
    Xiong D.-Y.
    Zhang M.
    Zhang, Min (minzhang@suda.edu.cn), 2018, Science Press (41): : 2734 - 2755
  • [25] Interactive neural machine translation
    Peris, Alvaro
    Domingo, Miguel
    Casacuberta, Francisco
    COMPUTER SPEECH AND LANGUAGE, 2017, 45 : 201 - 220
  • [26] Neural machine translation for Hungarian
    Laki, Laszlo Janos
    Yang, Zijian Gyozo
    ACTA LINGUISTICA ACADEMICA, 2022, 69 (04): : 501 - 520
  • [27] EXPLICITATION IN NEURAL MACHINE TRANSLATION
    Krueger, Ralph
    ACROSS LANGUAGES AND CULTURES, 2020, 21 (02) : 195 - 216
  • [28] Incorporating Statistical Machine Translation Word Knowledge Into Neural Machine Translation
    Wang, Xing
    Tu, Zhaopeng
    Zhang, Min
    IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2018, 26 (12) : 2255 - 2266
  • [29] Reduction of Neural Machine Translation Failures by Incorporating Statistical Machine Translation
    Dugonik, Jani
    Maucec, Mirjam Sepesy
    Verber, Domen
    Brest, Janez
    MATHEMATICS, 2023, 11 (11)
  • [30] Multi-Head Attention for End-to-End Neural Machine Translation
    Fung, Ivan
    Mak, Brian
    2018 11TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2018, : 250 - 254