A Joint Back-Translation and Transfer Learning Method for Low-Resource Neural Machine Translation
Joint Authors
Yang, Yating
Luo, Gong-Xu
Dong, Rui
Chen, Yan-Hong
Zhang, Wen-Bo
Source
Mathematical Problems in Engineering
Issue
Vol. 2020, Issue 2020 (31 Dec. 2020), pp.1-11, 11 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2020-05-31
Country of Publication
Egypt
No. of Pages
11
Main Subjects
Abstract EN
Neural machine translation (NMT) for low-resource languages has drawn great attention in recent years.
In this paper, we propose a joint back-translation and transfer learning method for low-resource languages.
It is widely recognized that data augmentation methods and transfer learning methods are both straight forward and effective ways for low-resource problems.
However, existing methods, which utilize one of these methods alone, limit the capacity of NMT models for low-resource problems.
In order to make full use of the advantages of existing methods and further improve the translation performance of low-resource languages, we propose a new method to perfectly integrate the back-translation method with mainstream transfer learning architectures, which can not only initialize the NMT model by transferring parameters of the pretrained models, but also generate synthetic parallel data by translating large-scale monolingual data of the target side to boost the fluency of translations.
We conduct experiments to explore the effectiveness of the joint method by incorporating back-translation into the parent-child and the hierarchical transfer learning architecture.
In addition, different preprocessing and training methods are explored to get better performance.
Experimental results on Uygur-Chinese and Turkish-English translation demonstrate the superiority of the proposed method over the baselines that use single methods.
American Psychological Association (APA)
Luo, Gong-Xu& Yang, Yating& Dong, Rui& Chen, Yan-Hong& Zhang, Wen-Bo. 2020. A Joint Back-Translation and Transfer Learning Method for Low-Resource Neural Machine Translation. Mathematical Problems in Engineering،Vol. 2020, no. 2020, pp.1-11.
https://search.emarefa.net/detail/BIM-1196542
Modern Language Association (MLA)
Luo, Gong-Xu…[et al.]. A Joint Back-Translation and Transfer Learning Method for Low-Resource Neural Machine Translation. Mathematical Problems in Engineering No. 2020 (2020), pp.1-11.
https://search.emarefa.net/detail/BIM-1196542
American Medical Association (AMA)
Luo, Gong-Xu& Yang, Yating& Dong, Rui& Chen, Yan-Hong& Zhang, Wen-Bo. A Joint Back-Translation and Transfer Learning Method for Low-Resource Neural Machine Translation. Mathematical Problems in Engineering. 2020. Vol. 2020, no. 2020, pp.1-11.
https://search.emarefa.net/detail/BIM-1196542
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1196542