Back to Search
Start Over
Convolutional Self-Attention Network
- Publication Year :
- 2018
-
Abstract
- Self-attention network (SAN) has recently attracted increasing interest due to its fully parallelized computation and flexibility in modeling dependencies. It can be further enhanced with multi-headed attention mechanism by allowing the model to jointly attend to information from different representation subspaces at different positions (Vaswani et al., 2017). In this work, we propose a novel convolutional self-attention network (CSAN), which offers SAN the abilities to 1) capture neighboring dependencies, and 2) model the interaction between multiple attention heads. Experimental results on WMT14 English-to-German translation task demonstrate that the proposed approach outperforms both the strong Transformer baseline and other existing works on enhancing the locality of SAN. Comparing with previous work, our model does not introduce any new parameters.<br />Comment: The least version of this paper has been uploaded to another link: arXiv:1904.03107
Details
- Database :
- OAIster
- Publication Type :
- Electronic Resource
- Accession number :
- edsoai.on1106318225
- Document Type :
- Electronic Resource