Scientific article
Open access

Bootstrapping a Statistical Speech Translator From a Rule-Based One

Published inLinguistic issues in language technology, vol. 5, no. 3
Publication date2012

We describe a series of experiments in which we start with English to French and English to Japanese versions of a rule-based speech translation system for a medical domain, and bootstrap corresponding statistical systems. Comparative evaluation reveals that the statistical systems are still slightly inferior to the rule-based ones, despite the fact that con- siderable effort has been invested in tuning both the recognition and translation components; however, a hybrid system is able to deliver a small but significant improvement in performance. In conclusion, we suggest that the hybrid architecture we describe potentially allows construction of limited-domain speech translation systems which combine substantial source-language coverage with high-precision translation.

  • Translation
  • Speech technology
  • Spoken language
Citation (ISO format)
RAYNER, Emmanuel et al. Bootstrapping a Statistical Speech Translator From a Rule-Based One. In: Linguistic issues in language technology, 2012, vol. 5, n° 3.
Main files (1)
Article (Published version)
  • PID : unige:75402
ISSN of the journal1945-3604

Technical informations

Creation09/20/2015 4:44:00 PM
First validation09/20/2015 4:44:00 PM
Update time03/14/2023 11:38:08 PM
Status update03/14/2023 11:38:08 PM
Last indexation08/29/2023 7:13:01 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack