Learning Adaptive Segmentation Policy for Simultaneous Translation

Ruiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu, Haifeng Wang


Abstract
Balancing accuracy and latency is a great challenge for simultaneous translation. To achieve high accuracy, the model usually needs to wait for more streaming text before translation, which results in increased latency. However, keeping low latency would probably hurt accuracy. Therefore, it is essential to segment the ASR output into appropriate units for translation. Inspired by human interpreters, we propose a novel adaptive segmentation policy for simultaneous translation. The policy learns to segment the source text by considering possible translations produced by the translation model, maintaining consistency between the segmentation and translation. Experimental results on Chinese-English and German-English translation show that our method achieves a better accuracy-latency trade-off over recently proposed state-of-the-art methods.
Anthology ID:
2020.emnlp-main.178
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2280–2289
Language:
URL:
https://aclanthology.org/2020.emnlp-main.178
DOI:
10.18653/v1/2020.emnlp-main.178
Bibkey:
Cite (ACL):
Ruiqing Zhang, Chuanqiang Zhang, Zhongjun He, Hua Wu, and Haifeng Wang. 2020. Learning Adaptive Segmentation Policy for Simultaneous Translation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2280–2289, Online. Association for Computational Linguistics.
Cite (Informal):
Learning Adaptive Segmentation Policy for Simultaneous Translation (Zhang et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.178.pdf
Video:
 https://slideslive.com/38939292