New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implementation of the paper "Jointly Learning to Align & Translate with Transformer" #1615
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Quick first pass of review.
We need to fix the audio codepath to handle the new options (see Travis unit test logs). |
…rformance checked
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A few additional comments.
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.