ABSTRACT
Adaptive Dialogue Systems can be seen as smart interfaces that typically use natural language (spoken or written) as a means of communication. They are being used in many applications, such as customer service, in-car interfaces, even in rehabilitation, and therefore it is essential that these systems are robust, scalable and quickly adaptable in order to cope with changing user or system needs or environmental conditions. Making Dialogue Systems adaptive means overcoming several challenges, such as scalability or lack of training data. Achieving adaptation online has thus been an even greater challenge. We propose to build such a system, that will operate in an Assistive Living Environment and provide its services as a coach to patients that need to perform rehabilitative exercises. We are currently in the process of developing it, using Robot Operating System on a robotic platform.
- Willow garage, http://www.willowgarage.com/pages/pr2/overview.Google Scholar
- M. Gasic, F. Jurcicek, S. Keizer, F. Mairesse, B. Thomson, K. Yu, and S. Young. Gaussian processes for fast policy optimisation of pomdp-based dialogue managers. In Proc. of the SIGDIAL 2010 Conf., page 201--204. ACL, 2010. Google ScholarDigital Library
- M. Geist and O. Pietquin. Kalman temporal differences. J. Artif. Int. Res., 39:483--532, September 2010. Google ScholarDigital Library
- A. Papangelis. A comparative study of reinforcement learning techniques on dialogue management. In Proc. of SRW at EACL, pages 22--31. ACL, 2012. Google ScholarDigital Library
- A. Papangelis, V. Karkaletsis, and F. Makedon. Evaluation of online dialogue policy learning techniques. In Proc. of the 8th LREC, 2012.Google Scholar
- A. Papangelis, V. Karkaletsis, and F. Makedon. Online complex action learning and user state estimation for adaptive dialogue systems. In Proc. of IEEE ICTAI, 2012. Google ScholarDigital Library
- A. Papangelis, N. Kouroupas, V. Karkaletsis, and F. Makedon. An adaptive dialogue system with online dialogue policy learning. In Artificial Intelligence: Theories and Applications, volume 7297 of LNCS, pages 323--330. 2012. Google ScholarDigital Library
- O. Pietquin, M. Geist, S. Chandramohan, and H. Frezza-Buet. Sample-Efficient Batch Reinforcement Learning for Dialogue Management Optimization. ACM TSLP, 7(3):7:1--7:21, May 2011. Google ScholarDigital Library
- M. Quigley, K. Conley, B. Gerkey, J. Faust, T. B. Foote, J. Leibs, R. Wheeler, and A. Y. Ng. ROS: an open-source robot operating system. In ICRA Workshop on Open Source Software, 2009.Google Scholar
Index Terms
- Towards adaptive dialogue systems for assistive living environments
Recommendations
From vocal to multimodal dialogue management
ICMI '06: Proceedings of the 8th international conference on Multimodal interfacesMultimodal, speech-enabled systems pose different research problems when compared to unimodal, voice-only dialogue systems. One of the important issues is the question of how a multimodal interface should look like in order to make the multimodal ...
Towards Conversationally Intelligent Dialog Systems
CHI EA '22: Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing SystemsSpoken dialog systems, lacking the means to address the complex phenomena of spontaneous speech and conversational dynamics, force users into a constrained mode of dialog that resembles text-based interaction more closely than spoken conversation. Turn-...
An adaptive dialogue system with online dialogue policy learning
SETN'12: Proceedings of the 7th Hellenic conference on Artificial Intelligence: theories and applicationsIn this work we present an architecture for Adaptive Dialogue Systems and a novel system that serves as a Museum Guide. It employs several online Reinforcement Learning (RL) techniques to achieve adaptation to the environment as well as to different ...
Comments