Name
Abstract | ||
|---|---|---|
Applications of Deep Belief Nets (DBN) to various problems have been the subject of a number of recent studies ranging from image classification and speech recognition to audio classification. In this study we apply DBNs to a natural language understanding problem. The recent surge of activity in this area was largely spurred by the development of a greedy layer-wise pretraining method that uses an efficient learning algorithm called Contrastive Divergence (CD). CD allows DBNs to 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 plain DBN-based model gives a call-routing classification accuracy that is equal to the best of the other models. However, using additional unlabeled data for DBN pre-training and combining DBN-based learned features with the original features provides significant gains over SVMs, which, in turn, performed better than both MaxEnt and Boosting. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TASLP.2014.2303296 | Audio, Speech, and Language Processing, IEEE/ACM Transactions |
Keywords | Field | DocType |
belief networks,feedforward neural nets,image classification,learning (artificial intelligence),natural language processing,speech recognition,CD,DBN,MaxEnt,SVM,audio classification,contrastive divergence,deep belief network application,feedforward neural network,image classification,learning algorithm,maximum entropy,natural language understanding,speech recognition,support vector machines,Call-Routing,DBN,Deep Learning,Deep Neural Nets,Natural language Understanding,RBM | Computer science,Deep belief network,Artificial intelligence,Deep learning,Contextual image classification,Artificial neural network,Pattern recognition,Support vector machine,Speech recognition,Boosting (machine learning),Statistical classification,Machine learning,Generative model | Journal |
Volume | Issue | ISSN |
22 | 4 | 2329-9290 |
Citations | PageRank | References |
83 | 2.32 | 12 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ruhi Sarikaya | 1 | 698 | 64.49 |
| geoffrey e hinton | 2 | 40435 | 4751.69 |
| Anoop Deoras | 3 | 240 | 29.36 |