Proceedings chapter
Open access

Developing Non-European Translation Pairs in a Medium-Vocabulary Medical Speech Translation System

Presented at Marrakech (Marocco), 28-30 May
Publication date2008

We describe recent work on MedSLT, a medium-vocabulary interlingua-based medical speech translation system, focussing on issues that arise when handling languages of which the grammar engineer has little or no knowledge. We describe how we can systematically create and maintain multiple forms of grammars, lexica and interlingual representations, with some versions being used by language informants, and some by grammar engineers. In particular, we describe the advantages of structuring the interlingua definition as a simple semantic grammar, which includes a human-readable surface form. We show how this allows us to rationalise the process of evaluating translations between languages lacking common speakers. The grammar-based interlingua definition can also be used in other ways. We describe two applications: a simple generic tool for debugging to-interlingua translation rules, and a method for improving speech understanding performance by rescoring N-best speech hypothesis lists. Examples presented focus on the concrete case of translation between Japanese and Arabic in both directions.

Citation (ISO format)
BOUILLON, Pierrette et al. Developing Non-European Translation Pairs in a Medium-Vocabulary Medical Speech Translation System. In: Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC). Marrakech (Marocco). [s.l.] : [s.n.], 2008. p. 1741–1748.
Main files (1)
Proceedings chapter
  • PID : unige:3467

Technical informations

Creation10/02/2009 9:29:01 AM
First validation10/02/2009 9:29:01 AM
Update time03/14/2023 3:14:55 PM
Status update03/14/2023 3:14:54 PM
Last indexation05/02/2024 11:19:28 AM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack