This repository has been archived by the owner on Nov 3, 2023. It is now read-only.
[BART] Do not add start/end tokens multiple times #3714
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
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Outdated suggestions cannot be applied.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.
Patch description
Found an issue with BART in which -- if we cache the text_vec -- start/end tokens are added multiple times. I was using this caching behavior to do "scoring" of candidates with BART, when we had too many candidates to fit in memory.
I adopted the same solution we use for BERT:
ParlAI/parlai/agents/bert_ranker/bi_encoder_ranker.py
Line 147 in c4c2669
CC @adamlerer
Testing steps
I added a test.