Adaptive Policy with Wait-k Model for Simultaneous Translation
Submission Type: Regular Long Paper
Submission Track: Machine Translation
Keywords: simultaneous machine translation, wait-k, adaptive policy, read/write supervision signals
TL;DR: We find the frozen multi-path wait-k model equipped with a plug-in read/write policy net trained with our proposed adaptive read/write supervision signals can achieve better accuracy-latency trade-off.
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.
Submission Number: 3235
Loading