UNIGE document Chapitre d'actes
previous document  unige:136491  next document
add to browser collection
Title

Ellipsis Translation for a Medical Speech to Speech Translation System

Authors
Published in 22nd Annual Conference of the European Association for Machine Translation (EAMT). Lisbon (Portugal) - November 3–5 2020 - . 2020
Abstract In diagnostic interviews, elliptical utterances allow doctors to question patients in a more efficient and economical way. However, literal translation of such incomplete utterances is rarely possible without affecting communication. Previous studies have focused on automatic ellipsis detection and resolution, but only few specifically address the problem of automatic translation of ellipsis. In this work, we evaluate four different approaches to translate ellipsis in medical dialogues in the context of the speech to speech translation system BabelDr. We also investigate the impact of training data, using an under-sampling method and data with elliptical utterances in context. Results show that the best model is able to translate 88% of elliptical utterances correctly.
Keywords Machine learningMachine translationEllipsis resolutionEllipsisMedical dialogBabelDr
Full text
Structures
Research group TIM/ISSCO
Citation
(ISO format)
MUTAL, Jonathan David et al. Ellipsis Translation for a Medical Speech to Speech Translation System. In: 22nd Annual Conference of the European Association for Machine Translation (EAMT). Lisbon (Portugal). [s.l.] : [s.n.], 2020. https://archive-ouverte.unige.ch/unige:136491

211 hits

56 downloads

Update

Deposited on : 2020-06-05

Export document
Format :
Citation style :