Investigation of Recurrent Neural Network Architectures and Learning Methods for Spoken Language Understanding
Based on the Interspeech '13 paper:
We also have a follow-up IEEE paper:
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.
In order to reproduce the results, make sure Theano is installed and run the following commands:
git clone git@github.com:aadamson/is13.git
cd is13
python examples/elman-forward.py
For running the Jordan architecture:
python examples/jordan-forward.py
For running the Deep RNN architecture:
python examples/deep-example.py
Note that running any of the examples will download all necessary data automatically.
import cPickle
train, test, dicts = cPickle.load(open("atis.pkl"))
dicts
is a python dictionnary that contains the mapping from the labels, the
name entities (if existing) and the words to indexes used in train
and test
lists. Refer to this tutorial for more details.
Running the following command can give you an idea of how the data has been preprocessed:
python data/load.py
Recurrent Neural Network Architectures for Spoken Language Understanding by Grégoire Mesnil is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Based on a work at https://github.com/mesnilgr/is13.