This repository has been archived by the owner on Dec 29, 2022. It is now read-only.
#174 fixed that unk_replacement and beam_search work together #271
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
|
Thanks for your pull request. It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). 📝 Please visit https://cla.developers.google.com/ to sign. Once you've signed, please reply here (e.g.
|
|
I signed it! |
|
CLAs look good, thanks! |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
The issue that unk_replacement and beam_search does not work is solved in this pull request.
The problem is that there is no attension_scores but multiple attension_scores in beam_search which is named "beam_search_output.original_outputs.attention_scores".
So I just added the procedures to pick one of them.
Since it seems that the top of the list is always the best among the beams in beam_search, [:,0,:] of it was taken.
This is my first big pull request and the code does not look beautiful, but I will appreciate if I could get kind instructions for this.