# Segmentation-Free Streaming Machine Translation

Source: [Segmentation-Free Streaming Machine Translation](<https://www.sota2.com/research/paper/68fa734f1e209131cea5bb6d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:47:16.604Z

Authors: Javier Iranzo-S\\'anchez, Jorge Iranzo-S\\'anchez, Adri\\\`a Gim\\'enez, Jorge Civera, Alfons Juan

Published: 2023-09-26T10:43:52.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2309.14823>)

[PDF](<https://arxiv.org/pdf/2309.14823.pdf>)
