Name
Abstract | ||
|---|---|---|
We propose Diverse Embedding Neural Network (DENN), a novel architecture for language models (LMs). A DENNLM projects the input word history vector onto multiple diverse low-dimensional sub-spaces instead of a single higher-dimensional sub-space as in conventional feed-forward neural network LMs. We encourage these sub-spaces to be diverse during network training through an augmented loss function. Our language modeling experiments on the Penn Treebank data set show the performance benefit of using a DENNLM. |
Year | Venue | Field |
|---|---|---|
2014 | International Conference on Learning Representations | Architecture,Embedding,Computer science,Neural network language models,Time delay neural network,Natural language processing,Treebank,Artificial intelligence,Artificial neural network,Machine learning,Language model |
DocType | Volume | Citations |
Journal | abs/1412.7063 | 0 |
PageRank | References | Authors |
0.34 | 3 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kartik Audhkhasi | 1 | 189 | 23.25 |
| Abhinav Sethy | 2 | 363 | 31.16 |
| Bhuvana Ramabhadran | 3 | 1779 | 153.83 |