Dialogue Modelling for a Conversational Agent
AI '01 Proceedings of the 14th Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
Juicer: a weighted finite-state transducer speech decoder
MLMI'06 Proceedings of the Third international conference on Machine Learning for Multimodal Interaction
IRIS: a chat-oriented dialogue system based on the vector space model
ACL '12 Proceedings of the ACL 2012 System Demonstrations
Movie-DiC: a movie dialogue corpus for research and development
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Short Papers - Volume 2
| Hi-index | 0.00 |
A technology demonstrator is one thing but having people use a technology is another, and the result reported here is that people often ignore our lovingly crafted handiwork. The SERA project - Social Engagement with Robots and Agents - was set up to look explicitly at what happens when a robot companion is put in someone's home. Even if things worked perfectly, there are times when a companion's human is simply not engaged. As a result we have separated our "dialog manager" into two parts: the dialog manager itself that determines what to say next, and an "interaction manager" that determines when to say it. This paper details the design of this SALT-E architecture.