Machine translation has enormous potential to improve communication across language barriers in the healthcare setting. We first explain what machine translation (MT) is, and why it has the potential to be useful in the health domain. We provide a brief account of the history of machine translation, covering the three main paradigms (rule-based, statistical and neural) and describe where the current state-of-the-art lies in relation to the goal of ‘fully automatic high-quality MT’. We identify different models of usage for MT (assimilation, post-editing) link these models with evaluation methods, and discuss their application to translation in health. We then describe a selection of research projects applying MT to the health domain, focusing most attention on two that we have personal acquaintance with: HimL and MedicalMT. Finally we present an outlook for the future of MT in the health domain.
|Title of host publication||The Routledge Handbook of Translation and Health|
|Editors||Şebnem Susam-Saraeva, Eva Spišiaková|
|Place of Publication||London|
|Number of pages||22|
|Publication status||Published - 10 May 2021|