Deep belief nets for natural language call-routing

This paper considers application of Deep Belief Nets (DBNs) to natural language call routing. DBNs have been successfully applied to a number of tasks, including image, audio and speech classification, thanks to the recent discovery of an efficient learning technique. DBNs learn a multi-layer generative model from unlabeled data and the features discovered by this model are then used to initialize a feed-forward neural network which is fine-tuned with backpropagation. We compare a DBN-initialized neural network to three widely used text classification algorithms; Support Vector machines (SVM), Boosting and Maximum Entropy (MaxEnt). The DBN-based model gives a call–routing classification accuracy that is equal to the best of the other models even though it currently uses an impoverished representation of the input.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabhadran
• Keywords: Deep Belief Nets, ICASSP 2011, Multi-layer Generative Model, Neural Network, Signal Processing