Trainable sentence planning for complex information presentation in spoken dialog systems

  • Authors:
  • Amanda Stent;Rashmi Prasad;Marilyn Walker

  • Affiliations:
  • Stony Brook University, Stony Brook, NY;University of Pennsylvania, Philadelphia, PA;University of Sheffield, Sheffield, U.K.

  • Venue:
  • ACL '04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

A challenging problem for spoken dialog systems is the design of utterance generation modules that are fast, flexible and general, yet produce high quality output in particular domains. A promising approach is trainable generation, which uses general-purpose linguistic knowledge automatically adapted to the application domain. This paper presents a trainable sentence planner for the MATCH dialog system. We show that trainable sentence planning can produce output comparable to that of MATCH's template-based generator even for quite complex information presentations.