Translation suggestion (TS) models are used to automatically provide alternative suggestions for incorrect spans in sentences generated by machine translation. This paper introduces the system used in our submission to the WMT'22 Translation Suggestion shared task. Our system is based on the ensemble of different translation architectures, including Transformer, SA-Transformer, and DynamicConv. We use three strategies to construct synthetic data from parallel corpora to compensate for the lack of supervised data. In addition, we introduce a multi-phase pre-training strategy, adding an additional pre-training phase with in-domain data. We rank second and third on the English-German and English-Chinese bidirectional tasks, respectively.
@article{arxiv.2210.06138,
title = {Improved Data Augmentation for Translation Suggestion},
author = {Hongxiao Zhang and Siyu Lai and Songming Zhang and Hui Huang and Yufeng Chen and Jinan Xu and Jian Liu},
journal= {arXiv preprint arXiv:2210.06138},
year = {2022}
}