- Notifications
You must be signed in to change notification settings - Fork14
Code for "Online and Linear Time Attention by Enforcing Monotonic Alignments"
License
NotificationsYou must be signed in to change notification settings
craffel/mad
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
NOTE - A reference implementation of the monotonic attention mechanism is now built into TensorFlow in thetf.contrib.seq2seq module. Seehere 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 thebenchmark folder) the synthetic benchmark used to compare the speed of the monotonic attention mechanism and standard softmax-based attention.