STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework

Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang


Abstract
Simultaneous translation, which translates sentences before they are finished, is use- ful in many scenarios but is notoriously dif- ficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we pro- pose a novel prefix-to-prefix framework for si- multaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very sim- ple yet surprisingly effective “wait-k” policy trained to generate the target sentence concur- rently with the source sentence, but always k words behind. Experiments show our strat- egy achieves low latency and reasonable qual- ity (compared to full-sentence translation) on 4 directions: zh↔en and de↔en.
Anthology ID:
P19-1289
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3025–3036
Language:
URL:
https://aclanthology.org/P19-1289
DOI:
10.18653/v1/P19-1289
Bibkey:
Cite (ACL):
Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, and Haifeng Wang. 2019. STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3025–3036, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (Ma et al., ACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/P19-1289.pdf
Code
 PaddlePaddle/PaddleNLP +  additional community code