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 13 条

[1]

[Anonymous], 2017, Transactions of the Association for Computational Linguistics, DOI [DOI 10.1162/TACL_A_00065, 10.1162/tacl_a_00065]

[2]

Axelrod Amittai, 2011, Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, P355

[3]

Bahdanau D, 2016, Arxiv, DOI [arXiv:1409.0473, DOI 10.48550/ARXIV.1409.0473]

[4]

Chen HG, 2017, Arxiv, DOI arXiv:1710.03282

[5]

Firat O, 2016, Arxiv, DOI arXiv:1606.04164

[6]

KALCHBRENNER N, 2013, P 2013 C EMP METH NA, P1700

[7]

Kim Y., 2016, P 2016 C EMP METH NA

[8] Ensemble-based classifiers [J].

Rokach, Lior .

ARTIFICIAL INTELLIGENCE REVIEW, 2010, 33 (1-2) :1-39

[9]

Sennrich R, 2016, PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, P86

[10]

Sennrich R, 2016, PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, P1715

← 1 2 →