en
Proceedings chapter
Open access
English

A Neural Machine Translation Approach to Translate Text to Pictographs in a Medical Speech Translation System - The BabelDr Use Case

Published inProceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas, Editors Kevin Duh, Francisco Guzman, Stephen Richardson, p. 252-263
Presented at Orlando, September 12-16, 2022
PublisherOrlando, USA : Association for Machine Translation in the Americas
First online date2022-09-12
Abstract

The use of images has been shown to positively affect patient comprehension in medical settings, in particular to deliver specific medical instructions. However, tools that automatically translate sentences into pictographs are still scarce due to the lack of resources. Previous studies have focused on the translation of sentences into pictographs by using WordNet combined with rule-based approaches and deep learning methods. In this work, we showed how we leveraged the BabelDr system, a speech to speech translator for medical triage, to build a speech to pictograph translator using UMLS and neural machine translation approaches. We showed that the translation from French sentences to a UMLS gloss can be viewed as a machine translation task and that a Multilingual Neural Machine Translation system achieved the best results.

eng
Keywords
  • Machine Translation
  • Deep Learning
  • Pictograph
  • UMLS
  • BabelDR
  • Medical Speech System
  • Human Evaluation
  • Automatic Evaluation
  • Accesibility
Research group
Citation (ISO format)
MUTAL, Jonathan David et al. A Neural Machine Translation Approach to Translate Text to Pictographs in a Medical Speech Translation System - The BabelDr Use Case. In: Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas. Orlando. Orlando, USA : Association for Machine Translation in the Americas, 2022. p. 252–263.
Main files (1)
Proceedings chapter (Published version)
Identifiers
  • PID : unige:163491
209views
81downloads

Technical informations

Creation09/21/2022 2:26:00 PM
First validation09/21/2022 2:26:00 PM
Update time03/16/2023 7:36:47 AM
Status update03/16/2023 7:36:46 AM
Last indexation02/01/2024 8:47:58 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack