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
来源
COMPUTER SPEECH AND LANGUAGE | 2017年 / 45卷
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
  • [1] EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation
    Xu, Yulin
    Yang, Zhen
    Meng, Fandong
    Zhou, Jie
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 8141 - 8153
  • [2] Multilingual Agreement for Multilingual Neural Machine Translation
    Yang, Jian
    Yin, Yuwei
    Ma, Shuming
    Huang, Haoyang
    Zhang, Dongdong
    Li, Zhoujun
    Wei, Furu
    ACL-IJCNLP 2021: THE 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 2, 2021, : 233 - 239
  • [3] Multi-task Learning for Multilingual Neural Machine Translation
    Wang, Yiren
    Zhai, ChengXiang
    Awadalla, Hany Hassan
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 1022 - 1034
  • [4] A Survey of Multilingual Neural Machine Translation
    Dabre, Raj
    Chu, Chenhui
    Kunchukuttan, Anoop
    ACM COMPUTING SURVEYS, 2020, 53 (05)
  • [5] Massively Multilingual Neural Machine Translation
    Aharoni, Roee
    Johnson, Melvin
    Firat, Orhan
    2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 3874 - 3884
  • [6] Multilingual Simultaneous Neural Machine Translation
    Arthur, Philip
    Ryu, Dongwon K.
    Haffari, Gholamreza
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 4758 - 4766
  • [7] Survey on Neural Machine Translation for multilingual translation system
    Basmatkar, Pranjali
    Holani, Hemant
    Kaushal, Shivani
    PROCEEDINGS OF THE 2019 3RD INTERNATIONAL CONFERENCE ON COMPUTING METHODOLOGIES AND COMMUNICATION (ICCMC 2019), 2019, : 443 - 448
  • [8] Multilingual Neural Machine Translation with Language Clustering
    Tan, Xu
    Chen, Jiale
    He, Di
    Xia, Yingce
    Qin, Tao
    Liu, Tie-Yan
    2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 963 - 973
  • [9] On the Pareto Front of Multilingual Neural Machine Translation
    Chen, Liang
    Ma, Shuming
    Zhang, Dongdong
    Wei, Furu
    Chang, Baobao
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [10] Cross-Species Translation of Multi-way Biomarkers
    Suvitaival, Tommi
    Huopaniemi, Ilkka
    Oresic, Matej
    Kaski, Samuel
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2011, PT I, 2011, 6791 : 209 - +