1. Attention is all you need[J];vaswani a;Advances in neural information processing systems,2017
2. Gradient-based learning applied to document recognition
3. A Review of Convolution-a1 Neural Network Research [J];yandong;Computer Applications,2016
4. Long Short-Term Memory
5. Neural machine translation by jointly learning to align and translate[J];bahdanau;ArXiv Preprint,2014