Authors: Mairesse, Francois
Walker, Marlyn
Title: Generating Individualized Utterances for Dialogue Systems
Language (ISO): en
Abstract: One of the most robust findings of studies of human-human dialogue is that people adapt their utterances to their conversational partners. However, spoken language generators are limited in their ability to adapt to individual users. While statistical models of language generation have the potential for individual adaptation, we know of no experiments showing this. In this paper, we utilize one statistical method, boosting, to train a spoken language generator for individual users. We show that individualized models perform better than models based on sets of users, and describe differences in the learned individual models arising from the linguistic preferences of users.
URI: http://hdl.handle.net/2003/21467
http://dx.doi.org/10.17877/DE290R-14199
Issue Date: 2005-06-13
Publisher: University of Dortmund
Is part of: Symposium on Dialogue Modelling and Generation at the 15th Annual meeting of the Society for Text and Discourse. Amsterdam, The Netherlands
Appears in Collections:Proceedings of the Symposium on Dialogue Modelling and Generation

Files in This Item:
File Description SizeFormat 
Mairesse.pdf148.42 kBAdobe PDFView/Open
Mairesse.ps1.45 MBPostscriptView/Open


This item is protected by original copyright



All resources in the repository are protected by copyright.