Segmentation-Free Streaming Machine Translation

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 s...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Iranzo-Sánchez, Javier, Iranzo-Sánchez, Jorge, Giménez, Adrià, Civera, Jorge, Alfons Juan
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.09.2023
Subjects
Automatic speech recognition
Machine translation
Segmentation
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422