-
Notifications
You must be signed in to change notification settings - Fork 324
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
Transformer Attention Probabilities #504
Closed
Closed
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
Changes by @tomsbergmanis Co-Authored-By: tomsbergmanis <tomsbergmanis@users.noreply.github.com>
tomsbergmanis
requested review from
davvil,
fhieber,
mjdenkowski and
tdomhan
as code owners
August 9, 2018 14:43
this introduces a lot of code repetition, as I'm actually changing |
Added max version constraint for numpy
Closing this PR as it would need to change the target branch to |
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Outdated suggestions cannot be applied.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.
This change adds attention probabilities for transformer decoder and completes TODO by @fhieber.
Specifically, we compute transformer attention probabilities as the average attention probabilities over all attention heads in all layers.
To do so, we create,
MultiHeadAttentionWithProbs
, a subclass ofMultiHeadAttention
which overrides_attend
to return attention probabilities.To evaluate the resulting attention probability matrices we used them as a basis for discrete word alignments. The resulting alignments were then compared against:
When conducting a human evaluation, we found that resulting word alignments are on average judged as acceptable as word alignments from LSTM attention matrices and strictly better than alignments by FastAlign.
Pull Request Checklist
until you can check this box.
pytest
)pytest test/system
)./style-check.sh
)sockeye/__init__.py
. Major version bump if this is a backwards incompatible change.By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.