An LSTM-based User Simulation Library for evaluating Statistical Dialogue Systems. Based on paper by Layla El Asri, Jing He, Kaheer Suleman at Maluuba Research, Montreal, Canda.
Uses Kera Deep Learning library with Tensorflow backend. https://keras.io/
Note: This script is meant to be used along with the DSTC2 dataset and not as a standalone.
References:
[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