%0 Conference Proceedings %T STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework %A Ma, Mingbo %A Huang, Liang %A Xiong, Hao %A Zheng, Renjie %A Liu, Kaibo %A Zheng, Baigong %A Zhang, Chuanqiang %A He, Zhongjun %A Liu, Hairong %A Li, Xing %A Wu, Hua %A Wang, Haifeng %Y Korhonen, Anna %Y Traum, David %Y Màrquez, Lluís %S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics %D 2019 %8 July %I Association for Computational Linguistics %C Florence, Italy %F ma-etal-2019-stacl %X 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. %R 10.18653/v1/P19-1289 %U https://aclanthology.org/P19-1289 %U https://doi.org/10.18653/v1/P19-1289 %P 3025-3036