Convolutional Sequence to Sequence Learning
This provides a more efficient and parallelizable alternative to recurrent models for machine translation, benefiting researchers and practitioners in natural language processing.
The paper tackled sequence-to-sequence learning by replacing recurrent neural networks with convolutional neural networks, achieving higher accuracy on WMT'14 English-German and English-French translation tasks while being an order of magnitude faster.
The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to recurrent models, computations over all elements can be fully parallelized during training and optimization is easier since the number of non-linearities is fixed and independent of the input length. Our use of gated linear units eases gradient propagation and we equip each decoder layer with a separate attention module. We outperform the accuracy of the deep LSTM setup of Wu et al. (2016) on both WMT'14 English-German and WMT'14 English-French translation at an order of magnitude faster speed, both on GPU and CPU.