Using a Deep Learning Dialogue Research Toolkit in a Multilingual Multidomain Practical Application
Abstract
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.
Cite
Text
Wilcock. "Using a Deep Learning Dialogue Research Toolkit in a Multilingual Multidomain Practical Application." International Joint Conference on Artificial Intelligence, 2018. doi:10.24963/IJCAI.2018/869Markdown
[Wilcock. "Using a Deep Learning Dialogue Research Toolkit in a Multilingual Multidomain Practical Application." International Joint Conference on Artificial Intelligence, 2018.](https://mlanthology.org/ijcai/2018/wilcock2018ijcai-using/) doi:10.24963/IJCAI.2018/869BibTeX
@inproceedings{wilcock2018ijcai-using,
title = {{Using a Deep Learning Dialogue Research Toolkit in a Multilingual Multidomain Practical Application}},
author = {Wilcock, Graham},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2018},
pages = {5880-5882},
doi = {10.24963/IJCAI.2018/869},
url = {https://mlanthology.org/ijcai/2018/wilcock2018ijcai-using/}
}