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.

翻译：流式机器翻译（Streaming Machine Translation, MT）旨在对无限输入的文本流进行实时翻译。传统的级联方法结合了自动语音识别（ASR）与MT系统，依赖于中间的分割步骤，将转录流切分为类似句子的单元。然而，引入硬性分割会限制MT系统，并成为错误的来源。本文提出了一种无分割框架，该框架通过将分割决策推迟至翻译生成之后，使模型能够直接翻译未分割的源语言流。大量实验表明，所提出的无分割框架在质量-延迟权衡上优于使用独立分割模型的竞争方法。相关软件、数据和模型将在论文接收后发布。