# Segmentation-Free Streaming Machine Translation

arXiv: https://arxiv.org/abs/2309.14823 · HTML: https://mlsanity.com/paper/2309.14823/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 26 Sep 2023.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Monotonic Infinite Lookback Attention for Simultaneous Machine Translation](https://mlsanity.com/paper/1906.05218/) (2019)
- [Neural Machine Translation with Extended Context](https://mlsanity.com/paper/1708.05943/) (2017)
- [Monotonic Multihead Attention](https://mlsanity.com/paper/1909.12406/) (2019)
- [Learning Compact Metrics for MT](https://mlsanity.com/paper/2110.06341/) (2021)
- [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)
- [Simultaneous Translation Policies: From Fixed to Adaptive](https://mlsanity.com/paper/2004.13169/) (2020)
- [Re-translation versus Streaming for Simultaneous Translation](https://mlsanity.com/paper/2004.03643/) (2020)
- [Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation](https://mlsanity.com/paper/1912.03393/) (2019)
- [Stream-level Latency Evaluation for Simultaneous Machine Translation](https://mlsanity.com/paper/2104.08817/) (2021)
- [Speculative Beam Search for Simultaneous Translation](https://mlsanity.com/paper/1909.05421/) (2019)
- [Sentence Boundary Augmentation For Neural Machine Translation Robustness](https://mlsanity.com/paper/2010.11132/) (2020)
- [From Simultaneous to Streaming Machine Translation by Leveraging Streaming History](https://mlsanity.com/paper/2203.02459/) (2022)
- [Neural Simultaneous Speech Translation Using Alignment-Based Chunking](https://mlsanity.com/paper/2005.14489/) (2020)
- [Simultaneous Translation for Unsegmented Input: A Sliding Window Approach](https://mlsanity.com/paper/2210.09754/) (2022)
- [Dynamic Masking for Improved Stability in Spoken Language Translation](https://mlsanity.com/paper/2006.00249/) (2020)
- [Simultaneous Neural Machine Translation with Constituent Label Prediction](https://mlsanity.com/paper/2110.13480/) (2021)

## Built on by (most cited first, 3 of 3)

- [How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?](https://mlsanity.com/paper/2412.18495/) (2024)
- [Overcoming Latency Bottlenecks in On-Device Speech Translation: A Cascaded Approach with Alignment-Based Streaming MT](https://mlsanity.com/paper/2508.13358/) (2025)
- [ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language Translation](https://mlsanity.com/paper/2610.03022/) (2026)

## Abstract (arXiv)

Streaming Machine Translation (MT) is the task of translating an unbounded input text stream in real-time. The traditional cascade approach, which combines an Automatic Speech Recognition (ASR) and an MT system, relies on an intermediate segmentation step which splits the transcription stream into sentence-like units. However, the incorporation of a hard segmentation constrains the MT system and is a source of errors. This paper proposes a Segmentation-Free framework that enables the model to translate an unsegmented source stream by delaying the segmentation decision until the translation has been generated. Extensive experiments show how the proposed Segmentation-Free framework has better quality-latency trade-off than competing approaches that use an independent segmentation model. Software, data and models will be released upon paper acceptance.