• Home
  1. Home
  2. Adapting a Medical Speech to Speech Translation System (MedSLT) to Arabic
Proceedings chapter
OA Policy
English

Adapting a Medical Speech to Speech Translation System (MedSLT) to Arabic

Contributors

Bouillon, Pierrette; Halimi Mallem, Ismahene Sonia; Rayner, Emmanuel; Hockey, Beth Ann

Presented at

Prague (Czech Republic), 27 June

Published in

Proceedings of the Workshop on Computational Approaches to Semitic Languages: Common Issues and Ressources, p. 41-48

Publication date

2007

Abstract

We describe the adaptation for Arabic of the grammar-based MedSLT medical speech system. The system supports simple medical diagnosis questions about headaches using vocabulary of 322 words. We show that the MedSLT architecture based on motivated general grammars produces very good results, with a limited effort. Based on the grammars for other languages covered by the system, it is in fact very easy to develop an Arabic grammar and to specialize it efficiently for the different system tasks. In this paper, we focus on generation.

UNIGE affiliation entities

Citation (ISO format)

BOUILLON, Pierrette et al. Adapting a Medical Speech to Speech Translation System (MedSLT) to Arabic. In: Proceedings of the Workshop on Computational Approaches to Semitic Languages: Common Issues and Ressources. Prague (Czech Republic). [s.l.] : [s.n.], 2007. p. 41–48. doi: 10.3115/1654576.1654584

Main files (1)

Proceedings chapter (Published version)

Identifiers

683views
513downloads

Technical informations

Creation

02/10/2009 09:28:51

First validation

02/10/2009 09:28:51

Update

29/01/2026 06:43:31

Status update

29/01/2026 06:43:31

Last indexation

29/01/2026 06:43:32
All rights reserved by Archive ouverte UNIGE and the University of Geneva
OpenAIRE Indexed & Validated