Abstract | ||
---|---|---|
Giving synthetic agents human-like realtime turntaking skills is a challenging task. Attempts have been made to manually construct such skills, with systematic categorization of silences, prosody and other candidate turn-giving signals, and to use analysis of corpora to produce static decision trees for this purpose. However, for general-purpose turntaking skills which vary between individuals and cultures, a system that can learn them on-the-job would be best. We are exploring ways to use machine learning to have an agent learn proper turntaking during interaction. We have implemented a talking agent that continuously adjusts its turntaking behavior to its interlocutors based on realtime analysis of the other party's prosody. Initial results from experiments on collaborative, content-free dialogue show that, for a given subset of turn-taking conditions, our modular reinforcement learning techniques allow the system to learn to take turns in an efficient, human-like manner. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-85483-8_17 | IVA |
Keywords | Field | DocType |
challenging task,general-purpose turntaking skill,synthetic agent,human-like turntaking,initial result,realtime analysis,proper turntaking,learning smooth,human-like manner,realtime turntaking skill,realtime dialogue,turntaking behavior,content-free dialogue show,reinforcement learning,decision tree,machine learning | Decision tree,Prosody,Categorization,Computer science,Natural language processing,Artificial intelligence,Modular design,Reinforcement learning | Conference |
Volume | ISSN | Citations |
5208 | 0302-9743 | 29 |
PageRank | References | Authors |
1.83 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gudny Ragna Jonsdottir | 1 | 64 | 6.15 |
Kristinn Thorisson | 2 | 658 | 94.55 |
Eric Nivel | 3 | 59 | 7.43 |