A robust and Efficient Threelayered Dialog Component for a Speech-to-Speech Translation System

Jan Alexandersson, Elisabeth Maier, Norbert Reithinger

In: Proceedings of the 7th Conference of the European Chapter of the ACL. Conference of the European Chapter of the Association for Computational Linguistics (EACL-95) March 27-31 Dublin Ireland 1995.


We present the dialogue component of the speech-to-speech translation system VERBMOBIL. In contrast to conventional dialogue systems it mediates the dialogue while processing maximally 50% of the dialogue in depth. Special requirements (robustness and efficiency) lead to a 3-layered hybrid architecture for the dialogue module, using statistics, an automaton and a planner. A dialogue memory is constructed incrementally.

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz