Name
Abstract | ||
|---|---|---|
In this paper, we explore different neural network architectures that can predict if a speaker of a given utterance is asking a question or making a statement. We com- pare the outcomes of regularization methods that are popularly used to train deep neural networks and study how different context functions can affect the classification performance. We also compare the efficacy of gated activation functions that are favorably used in recurrent neural networks and study how to combine multimodal inputs. We evaluate our models on two multimodal datasets: MSR-Skype and CALLHOME. |
Year | Venue | Field |
|---|---|---|
2015 | CoRR | Computer science,Recurrent neural network,Utterance,Speech recognition,Regularization (mathematics),Natural language processing,Artificial intelligence,Artificial neural network,Machine learning,Deep neural networks,Interrogative |
DocType | Volume | Citations |
Journal | abs/1511.01042 | 0 |
PageRank | References | Authors |
0.34 | 11 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Junyoung Chung | 1 | 1115 | 39.41 |
| Jacob Devlin | 2 | 738 | 32.34 |
| hany hassan awadalla | 3 | 0 | 1.01 |