Using a Deep Learning Dialogue Research Toolkit in a Multilingual Multidomain Practical Application

Using a Deep Learning Dialogue Research Toolkit in a Multilingual Multidomain Practical Application

Graham Wilcock

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

The demo shows a practical application of an open-source research toolkit developed by University of Cambridge. The toolkit (PyDial) supports research on deep reinforcement learning for multi-domain dialogues. The application (CityTalk) is a spoken dialogue system for robots that give information to tourists about local hotels and restaurants. We had a very positive experience using the toolkit, but in a few areas we decided to do things our own way.
Keywords:
Natural Language Processing: Speech
Natural Language Processing: Dialogue
Natural Language Processing: NLP Applications and Tools
Robotics and Vision: Human Robot Interaction