The dialog manager of a spoken dialog system often performs domain dependent functions as well as general dialog tasks. It is possible to separate the domain specific knowledge from knowledge about language using techniques from natural language generation. However a natural language generator often has to be tuned for particular applications. In this work, we describe a new method for automatically training the natural language generator and examine the role that domain specific and domain independent features have on performance. We show that although the general features have the largest impact, the use of domain specific features improves performance, while still retaining the benefits of automatic domain customization through training.
Cite as: Rogati, M., Walker, M., Rambow, O. (2001) Training a sentence planner for spoken dialog: the impact of syntactic and planning features. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1747-1750, doi: 10.21437/Eurospeech.2001-409
@inproceedings{rogati01_eurospeech,
author={Monica Rogati and Marilyn Walker and Owen Rambow},
title={{Training a sentence planner for spoken dialog: the impact of syntactic and planning features}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={1747--1750},
doi={10.21437/Eurospeech.2001-409}
}