Neural Machine Translation Based on Back-Translation for Multilingual Translation Evaluation Task

被引：1

作者：

Lai, Siyu ^{[1
]}

Yang, Yueting ^{[1
]}

Xu, Jin'an ^{[1
]}

Chen, Yufeng ^{[1
]}

Huang, Hui ^{[1
]}

机构：

[1] Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing, Peoples R China

来源：

MACHINE TRANSLATION, CCMT 2020 | 2020年 / 1328卷

基金：

中国国家自然科学基金;

关键词：

Machine translation; Multilingual machine translation;

D O I：

10.1007/978-981-33-6162-1_13

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents the systems developed by Beijing Jiaotong University for the CCMT 2020 multilingual translation evaluation task. For this translation task, we need to build a Japanese-English translation system based on only Japanese-Chinese and English-Chinese data. Our method mainly relies on synthetic data generated by back translation. We implemented three different architectures, namely Transformer-big, Transformer-base and Dynamic-Conv. We also implemented multi-model ensemble technique to further boost the final result. Experiments show that our machine translation system achieved high accuracy without relying on any bilingual training data.

引用

页码：132 / 141

页数：10

共 50 条

[1] Neural Machine Translation Based on Back-Translation for Multilingual Translation Evaluation Task
School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China
[J]. Commun. Comput. Info. Sci., (132-141):
[2] Iterative Back-Translation for Neural Machine Translation
Vu Cong Duy Hoang
Koehn, Philipp
Haffari, Gholamreza
Cohn, Trevor
[J]. NEURAL MACHINE TRANSLATION AND GENERATION, 2018, : 18 - 24
[3] Generalizing Back-Translation in Neural Machine Translation
Graca, Miguel
Kim, Yunsu
Schamper, Julian
Khadivi, Shahram
Ney, Hermann
[J]. FOURTH CONFERENCE ON MACHINE TRANSLATION (WMT 2019), VOL 1: RESEARCH PAPERS, 2019, : 45 - 52
[4] On The Evaluation of Machine Translation Systems Trained With Back-Translation
Edunov, Sergey
Ott, Myle
Ranzato, Marc'Aurelio
Auli, Michael
[J]. 58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 2836 - 2846
[5] Back-Translation Sampling by Targeting DifficultWords in Neural Machine Translation
Fadaee, Marzieh
Monz, Christof
[J]. 2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 436 - 446
[6] Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation
Wu, Jiawei
Wang, Xin
Wang, William Yang
[J]. 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, 2019, : 1173 - 1183
[7] Evaluation of the Validity of Back-Translation as a Method of Assessing the Accuracy of Machine Translation
Miyabe, Mai
Yoshino, Takashi
[J]. 2015 INTERNATIONAL CONFERENCE ON CULTURE AND COMPUTING (CULTURE COMPUTING), 2015, : 145 - 150
[8] On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation
Liu, Xuebo
Wang, Longyue
Wong, Derek F.
Ding, Liang
Chao, Lidia S.
Shi, Shuming
Tu, Zhaopeng
[J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2021, 2021, : 2900 - 2907
[9] Back-translation in Translation Teaching
刘聪
[J]. 读与写(教育教学刊), 2018, 15 (10) : 3 - 3
[10] A Joint Back-Translation and Transfer Learning Method for Low-Resource Neural Machine Translation
Luo, Gong-Xu
Yang, Ya-Ting
Dong, Rui
Chen, Yan-Hong
Zhang, Wen-Bo
[J]. MATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020 (2020)

← 1 2 3 4 5 →