A Simple and Effective Approach to Coverage-Aware Neural Machine Translation

被引:0
|
作者
Li, Yanyang [1 ]
Xiao, Tong [1 ]
Li, Yinqiao [1 ]
Wang, Qiang [1 ]
Xu, Changming [1 ]
Lu, Xueqiang [2 ]
机构
[1] Northeastern Univ, Nat Language Proc Lab, Boston, MA 02115 USA
[2] Beijing Key Lab Internet Culture & Digital Dissem, Beijing, Peoples R China
基金
美国国家科学基金会;
关键词
D O I
暂无
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
We offer a simple and effective method to seek a better balance between model confidence and length preference for Neural Machine Translation (NMT). Unlike the popular length normalization and coverage models, our model does not require training nor reranking the limited n-best outputs. Moreover, it is robust to large beam sizes, which is not well studied in previous work. On the Chinese-English and English-German translation tasks, our approach yields +0.4 similar to similar to 1.5 BLEU improvements over the state-of-the-art baselines.
引用
收藏
页码:292 / 297
页数:6
相关论文
共 50 条
  • [1] An Effective Coverage Approach for Attention-based Neural Machine Translation
    Hoang-Quan Nguyen
    Thuan-Minh Nguyen
    Huy-Hien Vu
    Van-Vinh Nguyen
    Phuong-Thai Nguyen
    Thi-Nga-My Dao
    Kieu-Hue Tran
    Khac-Quy Dinh
    [J]. PROCEEDINGS OF 2019 6TH NATIONAL FOUNDATION FOR SCIENCE AND TECHNOLOGY DEVELOPMENT (NAFOSTED) CONFERENCE ON INFORMATION AND COMPUTER SCIENCE (NICS), 2019, : 240 - 245
  • [2] Coverage-Aware Test Database Reduction
    Tuya, Javier
    de la Riva, Claudio
    Jose Suarez-Cabal, Maria
    Blanco, Raquel
    [J]. IEEE TRANSACTIONS ON SOFTWARE ENGINEERING, 2016, 42 (10) : 941 - 959
  • [3] A Coverage-Aware VNF Placement and Resource Allocation Approach for Disaggregated vRANs
    Lopes, Victor Hugo L.
    Almeida, Gabriel Matheus
    Klautau, Aldebaro
    Cardoso, Kleber
    [J]. 2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022), 2022, : 185 - 190
  • [4] Simple and Effective Noisy Channel Modeling for Neural Machine Translation
    Yee, Kyra
    Dauphin, Yann N.
    Auli, Michael
    [J]. 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, : 5696 - 5701
  • [5] Target Coverage-Aware Clustering in Directional Sensor Networks: A Distributed Approach
    Sharmin, Selina
    Nur, Fernaz Narin
    Islam, Maheen
    Razzaque, Md Abdur
    Hassan, Mohammad Mehedi
    Alelaiwi, Abdulhameed
    [J]. IEEE ACCESS, 2019, 7 : 64005 - 64014
  • [6] Modeling Coverage for Neural Machine Translation
    Tu, Zhaopeng
    Lu, Zhengdong
    Liu, Yang
    Liu, Xiaohua
    Li, Hang
    [J]. PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2016, : 76 - 85
  • [7] Optimal Coverage-Aware Hovering UAV Height
    Lohan, Poonam
    Mishra, Deepak
    Gupta, Neena
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ADVANCED NETWORKS AND TELECOMMUNICATIONS SYSTEMS (IEEE ANTS), 2021,
  • [8] Cellular Coverage-Aware Path Planning for UAVs
    De Bast, Sibren
    Vinogradov, Evgenii
    Pollin, Sofie
    [J]. 2019 IEEE 20TH INTERNATIONAL WORKSHOP ON SIGNAL PROCESSING ADVANCES IN WIRELESS COMMUNICATIONS (SPAWC 2019), 2019,
  • [9] Coverage-Aware Connectivity Restoration in Mobile Sensor Networks
    Tamboli, Neelofer
    Younis, Mohamed
    [J]. 2009 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS, VOLS 1-8, 2009, : 17 - 21
  • [10] Coverage-aware self-scheduling in sensor networks
    Lu, J
    Suda, T
    [J]. CCW 2003: IEEE 18TH ANNUAL WORKSHOP ON COMPUTER COMMUNICATIONS, PROCEEDINGS, 2003, : 117 - 123