Abstract | ||
---|---|---|
Neural machine translation (NMT) goes through rapid development because of the application of various deep learning techs. Especially, how to construct a more effective structure of NMT attracts more and more attention. Transformer is a state-of-the-art architecture in NMT. It replies on the self-attention mechanism exactly instead of recurrent neural networks (RNN). The Multi-head attention is a crucial part that implements the self-attention mechanism, and it also dramatically affects the scale of the model. In this paper, we present a new Multi-head attention by combining convolution operation. In comparison with the base Transformer, our approach can reduce the number of parameters effectively. And we perform a reasoned experiment. The result shows that the performance of the new model is similar to the base model. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/iCAST51195.2020.9319489 | 2020 11th International Conference on Awareness Science and Technology (iCAST) |
Keywords | DocType | ISSN |
neural machine translation,Transformer,CNN,Muti-head attention | Conference | 2325-5986 |
ISBN | Citations | PageRank |
978-1-7281-9120-1 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kungan Zeng | 1 | 0 | 0.34 |
Incheon Paik | 2 | 241 | 38.80 |