# Self-Modifying State Modeling for Simultaneous Machine Translation

arXiv: https://arxiv.org/abs/2406.02237 · HTML: https://mlsanity.com/paper/2406.02237/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [Learning Confidence for Out-of-Distribution Detection in Neural Networks](https://mlsanity.com/paper/1802.04865/) (2018)
- [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)
- [Can neural machine translation do simultaneous translation?](https://mlsanity.com/paper/1606.02012/) (2016)
- [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020)
- [Information-Transport-based Policy for Simultaneous Translation](https://mlsanity.com/paper/2210.12357/) (2022)
- [Sequence Length is a Domain: Length-based Overfitting in Transformer Models](https://mlsanity.com/paper/2109.07276/) (2021)
- [Improving Back-Translation with Uncertainty-based Confidence Estimation](https://mlsanity.com/paper/1909.00157/) (2019)
- [Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy](https://mlsanity.com/paper/2109.05238/) (2021)
- [Self-Paced Learning for Neural Machine Translation](https://mlsanity.com/paper/2010.04505/) (2020)
- [Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning](https://mlsanity.com/paper/2010.04314/) (2020)
- [Hidden Markov Transformer for Simultaneous Machine Translation](https://mlsanity.com/paper/2303.00257/) (2023)
- [Modeling Dual Read/Write Paths for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09163/) (2022)
- [Gaussian Multi-head Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09072/) (2022)
- [From Simultaneous to Streaming Machine Translation by Leveraging Streaming History](https://mlsanity.com/paper/2203.02459/) (2022)
- [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, 5 of 5)

- [SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation](https://mlsanity.com/paper/2505.20622/) (2025)
- [SimulPL: Aligning Human Preferences in Simultaneous Machine Translation](https://mlsanity.com/paper/2502.00634/) (2025)
- [Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation](https://mlsanity.com/paper/2501.00868/) (2025)
- [LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline](https://mlsanity.com/paper/2504.09570/) (2025)
- [Anticipating Future with Large Language Model for Simultaneous Machine Translation](https://mlsanity.com/paper/2410.22499/) (2024)

## Abstract (arXiv)

Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream source inputs and requires a read/write policy to decide whether to wait for the next source token or generate a new target token, whose decisions form a textitdecision path. Existing SiMT methods, which learn the policy by exploring various decision paths in training, face inherent limitations. These methods not only fail to precisely optimize the policy due to the inability to accurately assess the individual impact of each decision on SiMT performance, but also cannot sufficiently explore all potential paths because of their vast number. Besides, building decision paths requires unidirectional encoders to simulate streaming source inputs, which impairs the translation quality of SiMT models. To solve these issues, we propose Self-Modifying State Modeling (SM2), a novel training paradigm for SiMT task. Without building decision paths, SM2 individually optimizes decisions at each state during training. To precisely optimize the policy, SM2 introduces Self-Modifying process to independently assess and adjust decisions at each state. For sufficient exploration, SM2 proposes Prefix Sampling to efficiently traverse all potential states. Moreover, SM2 ensures compatibility with bidirectional encoders, thus achieving higher translation quality. Experiments show that SM2 outperforms strong baselines. Furthermore, SM2 allows offline machine translation models to acquire SiMT ability with fine-tuning.