Improving Stylized Neural Machine Translation with Iterative Dual Knowledge Transfer

Wu, Xuanxuan; Liu, Jian; Li, Xinjie; Xu, Jinan; Chen, Yufeng; Zhang, Yujie; Huang, Hui

doi:10.24963/ijcai.2021/547

Improving Stylized Neural Machine Translation with Iterative Dual Knowledge Transfer

Xuanxuan Wu, Jian Liu, Xinjie Li, Jinan Xu, Yufeng Chen, Yujie Zhang, Hui Huang

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3971-3977.

https://doi.org/10.24963/ijcai.2021/547

Keywords

Natural Language Processing: Natural Language Generation
Natural Language Processing: Machine Translation

Abstract

Stylized neural machine translation (NMT) aims to translate sentences of one style into sentences of another style, which is essential for the application of machine translation in a real-world scenario. However, a major challenge in this task is the scarcity of high-quality parallel data which is stylized paired. To address this problem, we propose an iterative dual knowledge transfer framework that utilizes informal training data of machine translation and formality style transfer data to create large-scale stylized paired data, for the training of stylized machine translation model. Specifically, we perform bidirectional knowledge transfer between translation model and text style transfer model iteratively through knowledge distillation. Then, we further propose a data-refinement module to process the noisy synthetic parallel data generated during knowledge transfer. Experiment results demonstrate the effectiveness of our method, achieving an improvement over the existing best model by 5 BLEU points on MTFC dataset. Meanwhile, extensive analyses illustrate our method can also improve the accuracy of formality style transfer.

Xuanxuan Wu, Jian Liu, Xinjie Li, Jinan Xu, Yufeng Chen, Yujie Zhang, and Hui Huang. 2021. Improving Stylized Neural Machine Translation with Iterative Dual Knowledge Transfer. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3971–3977. https://doi.org/10.24963/ijcai.2021/547

@inproceedings{ijcai2021p547,
  title     = {Improving Stylized Neural Machine Translation with Iterative Dual Knowledge Transfer},
  author    = {Wu, Xuanxuan and Liu, Jian and Li, Xinjie and Xu, Jinan and Chen, Yufeng and Zhang, Yujie and Huang, Hui},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {3971--3977},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/547},
  url       = {https://doi.org/10.24963/ijcai.2021/547},
}

TY  - CPAPER
TI  - Improving Stylized Neural Machine Translation with Iterative Dual Knowledge Transfer
AU  - Wu, Xuanxuan
AU  - Liu, Jian
AU  - Li, Xinjie
AU  - Xu, Jinan
AU  - Chen, Yufeng
AU  - Zhang, Yujie
AU  - Huang, Hui
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 3971
EP  - 3977
DO  - 10.24963/ijcai.2021/547
UR  - https://doi.org/10.24963/ijcai.2021/547
ER  -