This repository has been archived by the owner on Nov 22, 2022. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 801
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
implemented perplexity reductions for lm score reporting (#779)
Summary: Pull Request resolved: #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). Reviewed By: abhinavarora Differential Revision: D16244881 fbshipit-source-id: a579d27b7a17c0f52b0fa698f514db90be31694b
- Loading branch information
1 parent
fbf30bb
commit 4124119
Showing
2 changed files
with
40 additions
and
4 deletions.
There are no files selected for viewing
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
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