/Spoken-Language-Understanding-Using-LSTM

Final project for Deep Learning & Neural Networks course at Columbia University.

Primary LanguagePython

SPOKEN-LANGUAGE-UNDERSTANDING-USING-LSTM

For this project we have implemented most of the experiments in SPOKEN LANGUAGE UNDERSTANDING USING LONG SHORT-TERM MEMORY NEURAL NETWORKS [1] paper.

All the code and ipython notebooks are under src, data is under data and results are under results folders.

We tried to use exactly same data and parameters to get similar results, and for the most of the experiments we got +- 0.5% around the results on paper.

You can start reading from Standard LSTM notebook since this run is the base run, and explains how we proceeded for next experiments.

All our findings, comparisons to the original paper and some background knowledge are documented in report file above.

[1] K. Yao, B. Peng, Y. Zhang, D. Yu, G. Zweig, and Y. Shi, "SPOKEN LANGUAGE UNDERSTANDING USING LONG SHORT-TERM MEMORY NEURAL NETWORKS", IEEE, 2014.