file.pdf (49.63 kB)
Download file

Stochastic Language Generation for Spoken Dialogue Systems

Download (49.63 kB)
journal contribution
posted on 01.04.1995, 00:00 authored by Alice H Oh, Alexander RudnickyAlexander Rudnicky

The two current approaches to language generation, template-based and rule-based (linguistic) NLG, have limitations when applied to spoken dialogue systems, in part because they were developed for text generation. In this paper, we propose a new corpus-based approach to natural language generation, specifically designed for spoken dialogue systems.


Publisher Statement

All Rights Reserved



Usage metrics