Skip to content
PyTorch Implementation of "Monotonic Chunkwise Attention" (ICLR 2018)
Branch: master
Clone or download
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
imgs Update model figure Apr 2, 2018
Readme.md Edit readme: title Apr 2, 2018
attention.py
decoder.py Remove Variable: PyTorch 0.4 Apr 2, 2018
test.py Remove Variable: PyTorch 0.4 Apr 2, 2018

Readme.md

PyTorch Implementation of Monotonic Chunkwise Attention

Requirements

  • PyTorch 0.4

TODOs

  • Soft MoChA
  • Hard MoChA
  • Linear Time Decoding
  • Experiment with Real-world dataset

Model figure

Model figure 1

Linear Time Decoding

It's not clear if authors' TF implementation supports decoding in linear time. They calculate energies for whole encoder outputs instead of scanning from previously attended encoder output.

References

You can’t perform that action at this time.