# Incremental Decoding and Training Methods for Simultaneous Translation in Neural Machine Translation

arXiv: https://arxiv.org/abs/1806.03661 · HTML: https://mlsanity.com/paper/1806.03661/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2018.

## Built on by (most cited first, 30 of 52)

- [RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformer](https://mlsanity.com/paper/2106.04833/) (2021)
- [TransLLaMa: LLM-based Simultaneous Translation System](https://mlsanity.com/paper/2402.04636/) (2024)
- [Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy](https://mlsanity.com/paper/2109.05238/) (2021)
- [Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR](https://mlsanity.com/paper/2106.06636/) (2021)
- [Learning When to Translate for Streaming Speech](https://mlsanity.com/paper/2109.07368/) (2021)
- [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)
- [How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?](https://mlsanity.com/paper/2412.18495/) (2024)
- [Learning Optimal Policy for Simultaneous Machine Translation via Binary Search](https://mlsanity.com/paper/2305.12774/) (2023)
- [An Empirical Study of End-to-end Simultaneous Speech Translation Decoding Strategies](https://mlsanity.com/paper/2103.03233/) (2021)
- [Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation](https://mlsanity.com/paper/2210.11900/) (2022)
- [Chronological Thinking in Full-Duplex Spoken Dialogue Language Models](https://mlsanity.com/paper/2510.05150/) (2025)
- [Decoder-only Streaming Transformer for Simultaneous Translation](https://mlsanity.com/paper/2406.03878/) (2024)
- [Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning](https://mlsanity.com/paper/2002.04306/) (2020)
- [Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attention](https://mlsanity.com/paper/2110.08250/) (2021)
- [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)
- [Incremental Blockwise Beam Search for Simultaneous Speech Translation with Controllable Quality-Latency Tradeoff](https://mlsanity.com/paper/2309.11379/) (2023)
- [Efficient Monotonic Multihead Attention](https://mlsanity.com/paper/2312.04515/) (2023)
- [Exploiting Multimodal Reinforcement Learning for Simultaneous Machine Translation](https://mlsanity.com/paper/2102.11387/) (2021)
- [SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory](https://mlsanity.com/paper/2108.13630/) (2021)
- [Simultaneous Multi-Pivot Neural Machine Translation](https://mlsanity.com/paper/2104.07410/) (2021)
- [Tagged End-to-End Simultaneous Speech Translation Training using Simultaneous Interpretation Data](https://mlsanity.com/paper/2306.08582/) (2023)
- [Long-Form End-to-End Speech Translation via Latent Alignment Segmentation](https://mlsanity.com/paper/2309.11384/) (2023)
- [Anticipation-Free Training for Simultaneous Machine Translation](https://mlsanity.com/paper/2201.12868/) (2022)
- [Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation](https://mlsanity.com/paper/2104.14470/) (2021)
- [Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement](https://mlsanity.com/paper/2110.09646/) (2021)
- [Efficient Encoders for Streaming Sequence Tagging](https://mlsanity.com/paper/2301.09244/) (2023)
- [LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translation](https://mlsanity.com/paper/2303.11750/) (2023)

## Abstract (arXiv)

We address the problem of simultaneous translation by modifying the Neural MT decoder to operate with dynamically built encoder and attention. We propose a tunable agent which decides the best segmentation strategy for a user-defined BLEU loss and Average Proportion (AP) constraint. Our agent outperforms previously proposed Wait-if-diff and Wait-if-worse agents (Cho and Esipova, 2016) on BLEU with a lower latency. Secondly we proposed data-driven changes to Neural MT training to better match the incremental decoding framework.