Search Descriptions

Main Topics

Search Publications


author

title

other

year

Alternative Architectures

While the attentional sequence-to-sequence model is currently the dominant architecture for neural machine translation, other architectures have been explored.

Alternative Architectures is the main subject of 5 publications.

Publications

Kalchbrenner and Blunsom (2013) build a comprehensive machine translation model by first encoding the source sentence with a convolutional neural network, and then generate the target sentence by reversing the process. A refinement of this was proposed by Gehring et al. (2017) who use multiple convolutional layers in the encoder and the decoder that do not reduce the length of the encoded sequence but incorporate wider context with each layer.
Vaswani et al. (2017) replace the recurrent neural networks used in attentional sequence-to-sequence models with multiple self-attention layers, both for the encoder as well as the decoder.

Benchmarks

Discussion

Related Topics

New Publications

End-to-end

  • Pouget-Abadie et al. (2014)
  • Hill et al. (2014)

Actions

Download

Contribute