Paper: Trainable Sentence Planning For Complex Information Presentations In Spoken Dialog Systems

ACL ID P04-1011
Title Trainable Sentence Planning For Complex Information Presentations In Spoken Dialog Systems
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2004
Authors

A challenging problem for spoken dialog sys- tems is the design of utterance generation mod- ules that are fast, exible and general, yet pro- duce high quality output in particular domains. A promising approach is trainable generation, which uses general-purpose linguistic knowledge automatically adapted to the application do- main. This paper presents a trainable sentence planner for the MATCH dialog system. We show that trainable sentence planning can pro- duce output comparable to that of MATCH’s template-based generator even for quite com- plex information presentations.