@article{iranzo-sanchez-etal-2024-segmentation,
    title = "Segmentation-Free Streaming Machine Translation",
    author = "Iranzo-S{\'a}nchez, Javier  and
      Iranzo-S{\'a}nchez, Jorge  and
      Gim{\'e}nez, Adri{\`a}  and
      Civera, Jorge  and
      Juan, Alfons",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "12",
    year = "2024",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.tacl-1.61/",
    doi = "10.1162/tacl_a_00691",
    pages = "1104--1121",
    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 after 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.1"
}