Skip to content
forked from craffel/mad

Code for "Online and Linear Time Attention by Enforcing Monotonic Alignments"

License

Notifications You must be signed in to change notification settings

stefan-falk/mad

This branch is up to date with craffel/mad:master.

Repository files navigation

Online and Linear-Time Attention by Enforcing Monotonic Alignments

NOTE - A reference implementation of the monotonic attention mechanism is now built into TensorFlow in the tf.contrib.seq2seq module. See here for documentation.

This repository contains an example implementation of the monotonic alignment decoder proposed in "Online and Linear-Time Attention by Enforcing Monotonic Alignments", by Colin Raffel, Minh-Thang Luong, Peter J. Liu, Ron J. Weiss, and Douglas Eck (arXiv:1704.00784).

It also contains (in the benchmark folder) the synthetic benchmark used to compare the speed of the monotonic attention mechanism and standard softmax-based attention.

About

Code for "Online and Linear Time Attention by Enforcing Monotonic Alignments"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 85.0%
  • Python 12.8%
  • C++ 2.2%