# PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation

arXiv: https://arxiv.org/abs/2410.04075 · HTML: https://mlsanity.com/paper/2410.04075/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 5 Oct 2024.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [Does Simultaneous Speech Translation need Simultaneous Models?](https://mlsanity.com/paper/2204.03783/) (2022)
- [Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer Reorderings](https://mlsanity.com/paper/2010.11247/) (2020)
- [BSTC: A Large-Scale Chinese-English Speech Translation Dataset](https://mlsanity.com/paper/2104.03575/) (2021)
- [Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework](https://mlsanity.com/paper/2203.09053/) (2022)
- [Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation](https://mlsanity.com/paper/2210.11220/) (2022)
- [Learning Optimal Policy for Simultaneous Machine Translation via Binary Search](https://mlsanity.com/paper/2305.12774/) (2023)
- [Non-autoregressive Streaming Transformer for Simultaneous Translation](https://mlsanity.com/paper/2310.14883/) (2023)
- [Simultaneous Machine Translation with Tailored Reference](https://mlsanity.com/paper/2310.13588/) (2023)
- [Adaptive Policy with Wait-k Model for Simultaneous Translation](https://mlsanity.com/paper/2310.14853/) (2023)
- [Enhanced Simultaneous Machine Translation with Word-level Policies](https://mlsanity.com/paper/2310.16417/) (2023)

## Built on by (most cited first, 2 of 2)

- [From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Models](https://mlsanity.com/paper/2603.04592/) (2026)
- [SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation](https://mlsanity.com/paper/2509.01200/) (2025)

## Abstract (arXiv)

Simultaneous Machine Translation (SiMT) requires target tokens to be generated in real-time as streaming source tokens are consumed. Traditional approaches to SiMT typically require sophisticated architectures and extensive parameter configurations for training adaptive read/write policies, which in turn demand considerable computational power and memory. We propose PsFuture, the first zero-shot adaptive read/write policy for SiMT, enabling the translation model to independently determine read/write actions without the necessity for additional training. Furthermore, we introduce a novel training strategy, Prefix-to-Full (P2F), specifically tailored to adjust offline translation models for SiMT applications, exploiting the advantages of the bidirectional attention mechanism inherent in offline models. Experiments across multiple benchmarks demonstrate that our zero-shot policy attains performance on par with strong baselines and the P2F method can further enhance performance, achieving an outstanding trade-off between translation quality and latency.