This is a implement of Layla's short paper of Interspeech 2016
Mapper is not included, which makes it a different task and the result much higher comparing to the paper's report.
- Tensorflow
- Keras
DSTC2 dataset
http://camdial.org/~mh521/dstc/downloads/dstc2_traindev.tar.gz
[1] Layla El Asri, Jing He, and Kaheer Suleman. 2016. A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems. Interspeech 2016 (August 2016). DOI:http://dx.doi.org/10.21437/interspeech.2016-1175