Sciweavers

Share
ICASSP
2011
IEEE

Deep belief nets for natural language call-routing

10 years 5 months ago
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.
Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabha
Added 20 Aug 2011
Updated 20 Aug 2011
Type Journal
Year 2011
Where ICASSP
Authors Ruhi Sarikaya, Geoffrey E. Hinton, Bhuvana Ramabhadran
Comments (0)
books