Topic switch models for dialogue management in virtual humans

Zhu, Wenjue; Chowanda, Andry; Valstar, Michel F.

Abstract

This paper presents a novel data-driven Topic Switch Model based on a cognitive representation of a limited set of topics that are currently in-focus, which determines what utterances are chosen next. The transition model was statistically learned from a large set of transcribed dyadic interactions. Results show that using our proposed model results in interactions that on average last 2.17 times longer compared to the same system without our model.

Citation

Zhu, W., Chowanda, A., & Valstar, M. F. Topic switch models for dialogue management in virtual humans. Presented at 16th International Conference on Intelligent Virtual Agents (IVA 2016)

• Conference Name: 16th International Conference on Intelligent Virtual Agents (IVA 2016)
• End Date: Sep 23, 2016
• Acceptance Date: Jul 5, 2016
• Publication Date: Sep 20, 2016
• Deposit Date: Aug 2, 2016
• Publicly Available Date: Sep 20, 2016
• Peer Reviewed: Peer Reviewed
• Keywords: Social relationship, Framework, Game-agents, Interactions
• Public URL: https://nottingham-repository.worktribe.com/output/816969
• Publisher URL: http://www.springer.com/us/book/9783319476643
• Related Public URLs: http://iva2016.ict.usc.edu/; http://iva2016.ict.usc.edu/wp-content/uploads/Papers/100110390.pdf
• Contract Date: Aug 2, 2016