# Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapters

arXiv: https://arxiv.org/abs/2407.13469 · HTML: https://mlsanity.com/paper/2407.13469/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 18 Jul 2024.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [AdapterFusion: Non-Destructive Task Composition for Transfer Learning](https://mlsanity.com/paper/2005.00247/) (2020)
- [Learning multiple visual domains with residual adapters](https://mlsanity.com/paper/1705.08045/) (2017)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [Lifting the Curse of Multilinguality by Pre-training Modular Transformers](https://mlsanity.com/paper/2205.06266/) (2022)
- [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)
- [Can neural machine translation do simultaneous translation?](https://mlsanity.com/paper/1606.02012/) (2016)
- [Online and Linear-Time Attention by Enforcing Monotonic Alignments](https://mlsanity.com/paper/1704.00784/) (2017)
- [Efficient Wait-k Models for Simultaneous Machine Translation](https://mlsanity.com/paper/2005.08595/) (2020)
- [Norm-Based Curriculum Learning for Neural Machine Translation](https://mlsanity.com/paper/2006.02014/) (2020)
- [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)
- [Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy](https://mlsanity.com/paper/2109.05238/) (2021)
- [Future-Guided Incremental Transformer for Simultaneous Translation](https://mlsanity.com/paper/2012.12465/) (2020)
- [Language-Family Adapters for Low-Resource Multilingual Neural Machine Translation](https://mlsanity.com/paper/2209.15236/) (2022)
- [UDApter -- Efficient Domain Adaptation Using Adapters](https://mlsanity.com/paper/2302.03194/) (2023)
- [Stream-level Latency Evaluation for Simultaneous Machine Translation](https://mlsanity.com/paper/2104.08817/) (2021)
- [Adaptive Policy with Wait-k Model for Simultaneous Translation](https://mlsanity.com/paper/2310.14853/) (2023)
- [It is Not as Good as You Think! Evaluating Simultaneous Machine Translation on Interpretation Data](https://mlsanity.com/paper/2110.05213/) (2021)

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

- [Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies](https://mlsanity.com/paper/2601.11002/) (2026)
- [Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies](https://mlsanity.com/paper/2509.21801/) (2025)

## Abstract (arXiv)

Simultaneous machine translation aims at solving the task of real-time translation by starting to translate before consuming the full input, which poses challenges in terms of balancing quality and latency of the translation. The wait-k policy offers a solution by starting to translate after consuming k words, where the choice of the number k directly affects the latency and quality. In applications where we seek to keep the choice over latency and quality at inference, the wait-k policy obliges us to train more than one model. In this paper, we address the challenge of building one model that can fulfil multiple latency levels and we achieve this by introducing lightweight adapter modules into the decoder. The adapters are trained to be specialized for different wait-k values and compared to other techniques they offer more flexibility to allow for reaping the benefits of parameter sharing and minimizing interference. Additionally, we show that by combining with an adaptive strategy, we can further improve the results. Experiments on two language directions show that our method outperforms or competes with other strong baselines on most latency values.