Text Style Transfer Back-Translation
Daimeng Wei, Zhanglin Wu, Hengchao Shang, Zongyao Li, Minghan Wang, Jiaxin Guo, Xiaoyu Chen, Zhengzhe Yu, Hao Yang
Abstract
Back Translation (BT) is widely used in the field of machine translation, as it has been proved effective for enhancing translation quality. However, BT mainly improves the translation of inputs that share a similar style (to be more specific, translation-liked inputs), since the source side of BT data is machine-translated. For natural inputs, BT brings only slight improvements and sometimes even adverse effects. To address this issue, we propose Text Style Transfer Back Translation (TST BT), which uses a style transfer to modify the source side of BT data. By making the style of source-side text more natural, we aim to improve the translation of natural inputs. Our experiments on various language pairs, including both high-resource and low-resource ones, demonstrate that TST BT significantly improves translation performance against popular BT benchmarks. In addition, TST BT is proved to be effective in domain adaptation so this strategy can be regarded as a generalized data augmentation method. Our training code and text style transfer model are open-sourced.- Anthology ID:
- 2023.acl-long.441
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7944–7959
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.441
- DOI:
- 10.18653/v1/2023.acl-long.441
- Cite (ACL):
- Daimeng Wei, Zhanglin Wu, Hengchao Shang, Zongyao Li, Minghan Wang, Jiaxin Guo, Xiaoyu Chen, Zhengzhe Yu, and Hao Yang. 2023. Text Style Transfer Back-Translation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7944–7959, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Text Style Transfer Back-Translation (Wei et al., ACL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.441.pdf