Deep belief nets for natural language call-routing
Authors:
- 1 May 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 5680-5683
Abstract
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.Keywords
This publication has 10 references indexed in Scilit:
- A Practical Guide to Training Restricted Boltzmann Machines2012
- Learning multiple layers of representationTrends in Cognitive Sciences, 2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006
- A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 2006
- Exploiting unlabeled data using multiple classifiers for improved natural language call-routing2005
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- BoosTexter: A Boosting-based System for Text CategorizationMachine Learning, 2000
- A survey of smoothing techniques for ME modelsIEEE Transactions on Speech and Audio Processing, 2000
- Inducing features of random fieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- The Nature of Statistical Learning Theory1995