This repository was archived by the owner on Nov 22, 2022. It is now read-only.
implemented perplexity reductions for lm score reporting (old) #779
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
facebook-github-bot
added
the
CLA Signed
…earch#779) Summary: Pull Request resolved: facebookresearch#779 Implements perplexity reductions for language model score reporting. Currently, the reported score is the average perplexity of all words in a sentence, but this may not work for all use cases (e.g., the presence of named entities in a sentence brings up the average perplexity, so the resulting metric may not be as useful). To this end, this diff introduces several ways to "reduce" the perplexity scores of a sentence: min, max, mean, median, and eos (i.e., the perplexity of the `__END_OF_SENTENCE__` token). Differential Revision: D16244881 fbshipit-source-id: cd9126850a616a53c7f4cb241313764790b1222a
shreydesai
force-pushed
the
export-D16244881
branch
from
1823a41 to
8be6c27
Compare
|
This pull request has been merged in 4124119. |
shreydesai
changed the title
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Outdated suggestions cannot be applied.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.
Summary: Implements perplexity reductions for language model score reporting. Currently, the reported score is the average perplexity of all words in a sentence, but this may not work for all use cases (e.g., the presence of named entities in a sentence brings up the average perplexity, so the resulting metric may not be as useful). To this end, this diff introduces several ways to "reduce" the perplexity scores of a sentence: min, max, mean, median, and eos (i.e., the perplexity of the
__END_OF_SENTENCE__token).Differential Revision: D16244881