Paper: A Robust And Efficient Three-Layered Dialogue Component For A Speech-To-Speech Translation System

ACL ID E95-1026
Title A Robust And Efficient Three-Layered Dialogue Component For A Speech-To-Speech Translation System
Venue Annual Meeting of The European Chapter of The Association of Computational Linguistics
Session Main Conference
Year 1995
Authors

We present the dialogue component of the speech-to-speech translation system VERBMOBIL. In contrast to conventional dialogue systems it mediates the dia- logue while processing maximally 50% of the dialogue in depth. Special require- ments (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.