Code for RNN and Spoken Language Understanding

Based on the Interspeech '13 paper:

Gregoire Mesnil, Xiaodong He, Li Deng and Yoshua Bengio Investigation of Recurrent Neural Network Architectures and Learning Methods for Spoken Language Understanding

http://www.iro.umontreal.ca/~lisa/pointeurs/RNNSpokenLanguage2013.pdf

This code allows to get state-of-the-art results and a significant improvement (+1% in F1-score) with respect to the results presented in the paper.