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. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICASSP.2011.5947649 | Acoustics, Speech and Signal Processing |
Keywords | Field | DocType |
backpropagation,belief networks,feedforward neural nets,maximum entropy methods,natural language processing,support vector machines,DBN,SVM,deep belief nets,feed-forward neural network,learning technique,maximum entropy,multilayer generative model,natural language call routing,support vector machine,Call-Routing,DBN,Deep Learning,RBM | Pattern recognition,Computer science,Support vector machine,Natural language,Artificial intelligence,Boosting (machine learning),Deep learning,Backpropagation,Statistical classification,Artificial neural network,Machine learning,Generative model | Conference |
ISSN | ISBN | Citations |
1520-6149 E-ISBN : 978-1-4577-0537-3 | 978-1-4577-0537-3 | 29 |
PageRank | References | Authors |
1.08 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ruhi Sarikaya | 1 | 698 | 64.49 |
geoffrey e hinton | 2 | 40435 | 4751.69 |
Bhuvana Ramabhadran | 3 | 1779 | 153.83 |