홈 › Papers

Text Style Transfer Back-Translation

2023-06-02 · Daimeng Wei, Zhanglin Wu, Hengchao Shang, Zongyao Li, Minghan Wang, Jiaxin Guo, Xiaoyu Chen, Zhengzhe Yu, Hao Yang

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-like 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 model 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 general data augmentation method. Our training code and text style transfer model are open-sourced.

📄 PDF Abstract BibTeX arXiv:2306.01318

Code (1)

frxxzhl/ssebt 공식 구현 tf

Tasks

Data Augmentation Domain Adaptation Machine Translation Style Transfer Text Style Transfer Translation

Style Transfer as Unsupervised Machine Translation

2018-08-23 · Zhirui Zhang, Shuo Ren, Shujie Liu, Jianyong Wang 외

Language style transferring rephrases text with specific stylistic attributes while preserving the original attribute-independent content. One main challenge in learning a style transfer system is a lack of parallel data…

Attribute Machine Translation NMT Sentence+3

Style Transfer Through Back-Translation

2018-04-24 · ACL 2018 7 · Shrimai Prabhumoye, Yulia Tsvetkov, Ruslan Salakhutdinov, Alan W. black

Style transfer is the task of rephrasing the text to contain specific stylistic properties without changing the intent or affect within the context. This paper introduces a new method for automatic style transfer. We fir…

Sentence Style Transfer Text Style Transfer Translation

Empirical Evaluation of Supervision Signals for Style Transfer Models

2021-01-15 · Yevgeniy Puzikov, Simoes Stanley, Iryna Gurevych, Immanuel Schweizer

Text style transfer has gained increasing attention from the research community over the recent years. However, the proposed approaches vary in many ways, which makes it hard to assess the individual contribution of the …

Machine Translation reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+3

Image Translation via Fine-grained Knowledge Transfer

2020-12-21 · Xuanhong Chen, Ziang Liu, Ting Qiu, Bingbing Ni 외

Prevailing image-translation frameworks mostly seek to process images via the end-to-end style, which has achieved convincing results. Nonetheless, these methods lack interpretability and are not scalable on different im…

Retrieval Style Transfer Transfer Learning Translation

Time-of-Day Neural Style Transfer for Architectural Photographs

2022-09-13 · Yingshu Chen, Tuan-Anh Vu, Ka-Chun Shum, Binh-Son Hua 외

Architectural photography is a genre of photography that focuses on capturing a building or structure in the foreground with dramatic lighting in the background. Inspired by recent successes in image-to-image translation…

Image-to-Image Translation Style Transfer Translation