Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
This addresses machine translation efficiency and performance for NLP applications, offering a simpler alternative to existing methods.
The paper tackled the problem of sequence-to-sequence prediction in machine translation by replacing encoder-decoder architectures with a single 2D convolutional neural network, resulting in outperforming state-of-the-art systems with fewer parameters.
Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore pervasive throughout the network. Our model yields excellent results, outperforming state-of-the-art encoder-decoder systems, while being conceptually simpler and having fewer parameters.