Adaptive Policy with Wait-$k$ Model for Simultaneous Translation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationTranslationSimilar Papers 제목 키워드 기반
Data-Driven Adaptive Simultaneous Machine Translation
In simultaneous translation (SimulMT), the most widely used strategy is the wait-k policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, wait-k suffers from two major li…
Machine TranslationSentenceTranslationData-Driven Adaptive Simultaneous Machine Translation
In simultaneous translation (SimulMT), the most widely used strategy is the \waitk policy thanks to its simplicity and effectiveness in balancing translation quality and latency. However, \waitk suffers from two major li…
Machine TranslationSentenceTranslationLEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation
Simultaneous machine translation, which aims at a real-time translation, is useful in many live scenarios but very challenging due to the trade-off between accuracy and latency. To achieve the balance for both, the model…
Machine TranslationSentenceTranslationUniversal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy
Simultaneous machine translation (SiMT) generates translation before reading the entire source sentence and hence it has to trade off between translation quality and latency. To fulfill the requirements of different tran…
Machine TranslationMixture-of-ExpertsSentenceTranslationLearning Adaptive Segmentation Policy for Simultaneous Translation
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. …
SegmentationTranslation