# Adaptive Policy with Wait-k Model for Simultaneous Translation

arXiv: https://arxiv.org/abs/2310.14853 · HTML: https://mlsanity.com/paper/2310.14853/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 32 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Monotonic Infinite Lookback Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/1906.05218/) (2019)
- [Learning to Translate in Real-time with Neural Machine Translation](https://mlsanity.com/paper/1610.00388/) (2016)
- [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019)
- [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020)
- [Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation](https://mlsanity.com/paper/1806.03661/) (2018)
- [Simultaneous Translation Policies: From Fixed to Adaptive](https://mlsanity.com/paper/2004.13169/) (2020)
- [Information-Transport-based Policy for Simultaneous Translation](https://mlsanity.com/paper/2210.12357/) (2022)
- [Simpler and Faster Learning of Adaptive Policies for Simultaneous Translation](https://mlsanity.com/paper/1909.01559/) (2019)
- [Future-Guided Incremental Transformer for Simultaneous Translation](https://mlsanity.com/paper/2012.12465/) (2020)
- [Hidden Markov Transformer for Simultaneous Machine Translation](https://mlsanity.com/paper/2303.00257/) (2023)
- [BSTC: A Large-Scale Chinese-English Speech Translation Dataset](https://mlsanity.com/paper/2104.03575/) (2021)
- [Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation](https://mlsanity.com/paper/2210.11220/) (2022)
- [Lattice Transformer for Speech Translation](https://mlsanity.com/paper/1906.05551/) (2019)
- [Learning Optimal Policy for Simultaneous Machine Translation via Binary Search](https://mlsanity.com/paper/2305.12774/) (2023)
- [Adapting Offline Speech Translation Models for Streaming with Future-Aware Distillation and Inference](https://mlsanity.com/paper/2303.07914/) (2023)
- [Neural Machine Translation with Dynamic Graph Convolutional Decoder](https://mlsanity.com/paper/2305.17698/) (2023)

## Built on by (most cited first, 9 of 9)

- [Anchor-based Large Language Models](https://mlsanity.com/paper/2402.07616/) (2024)
- [Decoder-only Streaming Transformer for Simultaneous Translation](https://mlsanity.com/paper/2406.03878/) (2024)
- [Self-Modifying State Modeling for Simultaneous Machine Translation](https://mlsanity.com/paper/2406.02237/) (2024)
- [LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline](https://mlsanity.com/paper/2504.09570/) (2025)
- [Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models](https://mlsanity.com/paper/2406.06910/) (2024)
- [Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters](https://mlsanity.com/paper/2407.13469/) (2024)
- [PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation](https://mlsanity.com/paper/2410.04075/) (2024)
- [Dual-Stream Simultaneous Translation via 2D Grid Attention](https://mlsanity.com/paper/2609.34902/) (2026)
- [Towards Efficient Simultaneous Inverse Text Normalization with Pretrained Text-to-Text Language Model and Read-Tag-Write Policy](https://mlsanity.com/paper/2610.19492/) (2026)

## Abstract (arXiv)

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.