Adaptive Policy with Wait-k Model for Simultaneous Translation

Libo Zhao, Kai Fan, Wei Luo, Wu Jing, Shushu Wang, Ziqian Zeng, Zhongqiang Huang


Abstract
Simultaneous machine translation (SiMT) requires a robust read/write policy in conjunction with a high-quality translation model. Traditional methods rely on either a fixed wait-k policy coupled with a standalone wait-k translation model, or an adaptive policy jointly trained with the translation model. In this study, we propose a more flexible approach by decoupling the adaptive policy model from the translation model. Our motivation stems from the observation that a standalone multi-path wait-k model performs competitively with adaptive policies utilized in state-of-the-art SiMT approaches. Specifically, we introduce DaP, a divergence-based adaptive policy, that makes read/write decisions for any translation model based on the potential divergence in translation distributions resulting from future information. DaP extends a frozen wait-k model with lightweight parameters, and is both memory and computation efficient. Experimental results across various benchmarks demonstrate that our approach offers an improved trade-off between translation accuracy and latency, outperforming strong baselines.
Anthology ID:
2023.emnlp-main.293
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4816–4832
Language:
URL:
https://aclanthology.org/2023.emnlp-main.293
DOI:
10.18653/v1/2023.emnlp-main.293
Bibkey:
Cite (ACL):
Libo Zhao, Kai Fan, Wei Luo, Wu Jing, Shushu Wang, Ziqian Zeng, and Zhongqiang Huang. 2023. Adaptive Policy with Wait-k Model for Simultaneous Translation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4816–4832, Singapore. Association for Computational Linguistics.
Cite (Informal):
Adaptive Policy with Wait-k Model for Simultaneous Translation (Zhao et al., EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2023.emnlp-main.293.pdf
Video:
 https://preview.aclanthology.org/naacl-24-ws-corrections/2023.emnlp-main.293.mp4