Non-Autoregressive Machine Translation with Auxiliary Regularization

被引:0
|
作者
Wang, Yiren [1 ]
Tian, Fei [2 ]
He, Di [3 ]
Qin, Tao [2 ]
Zhai, ChengXiang [1 ]
Liu, Tie-Yan [2 ]
机构
[1] Univ Illinois, Urbana, IL 61801 USA
[2] Microsoft Res, Beijing, Peoples R China
[3] Peking Univ, Key Lab Machine Percept, MOE, Sch EECS, Beijing, Peoples R China
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
As a new neural machine translation approach, Non-Autoregressive machine Translation (NAT) has attracted attention recently due to its high efficiency in inference. However, the high efficiency has come at the cost of not capturing the sequential dependency on the target side of translation, which causes NAT to suffer from two kinds of translation errors: 1) repeated translations (due to indistinguishable adjacent decoder hidden states), and 2) incomplete translations (due to incomplete transfer of source side information via the decoder hidden states). In this paper, we propose to address these two problems by improving the quality of decoder hidden representations via two auxiliary regularization terms in the training process of an NAT model. First, to make the hidden states more distinguishable, we regularize the similarity between consecutive hidden states based on the corresponding target tokens. Second, to force the hidden states to contain all the information in the source sentence, we leverage the dual nature of translation tasks (e.g., English to German and German to English) and minimize a backward reconstruction error to ensure that the hidden states of the NAT decoder are able to recover the source side sentence. Extensive experiments conducted on several benchmark datasets show that both regularization strategies are effective and can alleviate the issues of repeated translations and incomplete translations in NAT models. The accuracy of NAT models is therefore improved significantly over the state-of-the-art NAT models with even better efficiency for inference.
引用
收藏
页码:5377 / 5384
页数:8
相关论文
共 50 条
  • [1] Non-autoregressive neural machine translation with auxiliary representation fusion
    Du, Quan
    Feng, Kai
    Xu, Chen
    Xiao, Tong
    Zhu, Jingbo
    [J]. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2021, 41 (06) : 7229 - 7239
  • [2] Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational Framework
    Zhu, Minghao
    Wang, Junli
    Yan, Chungang
    [J]. NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 607 - 617
  • [3] Integrating Translation Memories into Non-Autoregressive Machine Translation
    Xu, Jitao
    Crego, Josep
    Yvon, Francois
    [J]. 17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 1326 - 1338
  • [4] Enhanced encoder for non-autoregressive machine translation
    Wang, Shuheng
    Shi, Shumin
    Huang, Heyan
    [J]. MACHINE TRANSLATION, 2021, 35 (04) : 595 - 609
  • [5] Acyclic Transformer for Non-Autoregressive Machine Translation
    Huang, Fei
    Zhou, Hao
    Liu, Yang
    Li, Hang
    Huang, Minlie
    [J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [6] A Survey of Non-Autoregressive Neural Machine Translation
    Li, Feng
    Chen, Jingxian
    Zhang, Xuejun
    [J]. ELECTRONICS, 2023, 12 (13)
  • [7] Non-Autoregressive Machine Translation with Latent Alignments
    Saharia, Chitwan
    Chan, William
    Saxena, Saurabh
    Norouzi, Mohammad
    [J]. PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 1098 - 1108
  • [8] Modeling Coverage for Non-Autoregressive Neural Machine Translation
    Shan, Yong
    Feng, Yang
    Shao, Chenze
    [J]. 2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [9] Incorporating history and future into non-autoregressive machine translation
    Wang, Shuheng
    Huang, Heyan
    Shi, Shumin
    [J]. COMPUTER SPEECH AND LANGUAGE, 2022, 77
  • [10] Glancing Transformer for Non-Autoregressive Neural Machine Translation
    Qian, Lihua
    Zhou, Hao
    Bao, Yu
    Wang, Mingxuan
    Qiu, Lin
    Zhang, Weinan
    Yu, Yong
    Li, Lei
    [J]. 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 (ACL-IJCNLP 2021), 2021, : 1993 - 2003