Move trg_embedder inside decoder #560
Merged
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
added 7 commits
December 6, 2018 10:11
|
I can take a look at this, but would you mind adjusting the |
msperber
requested changes
Jan 4, 2019
There was a problem hiding this comment.
This looks good and makes sense to me. Could you make sure the configs under the example/ folder (including the programmatic example) and the recipes/ folder are up to date? Also, the docs (experiment_config_files, translator_structure) would need some small updates. With those I think this will be good to merge!
added 4 commits
January 9, 2019 15:25
msperber
approved these changes
Jan 10, 2019
|
LGTM, please feel free to merge! |
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Outdated suggestions cannot be applied.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.
See Issue 556.
This PR moves the trg_embedder inside the decoder, and gives the decoder access to the raw sequence of tokens. This is particularly useful if the decoder is generating e.g. a series of RNNG actions, and not simply a linear sequence of words to be embedded.