Implementation of the paper "Jointly Learning to Align & Translate with Transformer" #1615
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
We need to fix the audio codepath to handle the new options (see Travis unit test logs). |
…rformance checked
francoishernandez
pushed a commit
to KaijuML/OpenNMT-py
that referenced
this pull request
Dec 12, 2019
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implementation of the paper https://arxiv.org/abs/1909.02074 using OpenNMT-py.
Original implementation disponible at fairseq.
This PR enables Transformer based models to jointly output word alignment alongside its translation.
The quality of output alignment could be further improved by joint training models on translation & alignment providing align labels produced by statistic tools such as fastalign or giza.