English

A Robust and Efficient Three-Layered Dialogue Component for a Speech-to-Speech Translation System

cmp-lg 2016-08-31 v1 Computation and Language

Abstract

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 like 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.

Keywords

Cite

@article{arxiv.cmp-lg/9502008,
  title  = {A Robust and Efficient Three-Layered Dialogue Component for a Speech-to-Speech Translation System},
  author = {Jan Alexandersson and Elisabeth Maier and Norbert Reithinger},
  journal= {arXiv preprint arXiv:cmp-lg/9502008},
  year   = {2016}
}

Comments

Postscript file, compressed and uuencoded, 15 pages, to appear in Proceedings of EACL-95, Dublin.

R2 v1 2026-07-22T09:58:02.714Z