Improved Data Augmentation for Translation Suggestion

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 en...

Full description

Saved in:
Bibliographic Details
Main Authors Zhang, Hongxiao, Lai, Siyu, Zhang, Songming, Huang, Hui, Chen, Yufeng, Xu, Jinan, Liu, Jian
Format Journal Article
LanguageEnglish
Published 12.10.2022
Subjects
Computer Science - Computation and Language
Online AccessGet full text

Cover

More Information
Summary: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.
DOI:10.48550/arxiv.2210.06138