Remove normalization of confidence scores in intent classification #782
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
The logreg intent classifier used to have a specific logic when used with an intents filter: the intent classification scores were renormalized to sum to 1.0. This could lead to unexpected behaviors, especially when all the intents in the intents filter are associated to very low confidence scores. In such cases, the renormalization would significantly increase the scores.
Codecov Report
@@ Coverage Diff @@
## develop #782 +/- ##
===========================================
+ Coverage 88.1% 88.22% +0.11%
===========================================
Files 76 76
Lines 4541 4576 +35
Branches 871 904 +33
===========================================
+ Hits 4001 4037 +36
+ Misses 403 401 -2
- Partials 137 138 +1 |
ClemDoum
approved these changes
Apr 5, 2019
Merged
# for free
to join this conversation on GitHub.
Already have an account?
# 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Outdated suggestions cannot be applied.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.
Description:
The logreg intent classifier used to have a specific logic when used with an intents filter: the intent classification scores were renormalized to sum to 1.0.
This could lead to unexpected behaviors, especially when all the intents in the intents filter are associated to very low confidence scores. In such cases, the renormalization would significantly increase the scores.
Checklist: