Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Confidence score changes in Entity Classifier #473

Merged
merged 9 commits into from
Aug 13, 2024

Conversation

gr8nishan
Copy link
Collaborator

This PR has changes related to entity classification improvement by changing the threshold for certain PII

Changes we have done->

  1. Confidence score of below three entities have been reduced from 0.8 to 0.4

    US_PASSPORT
    US_BANK_NUMBER
    US_DRIVER_LICENSE
  2. Confidence score of AWS_ACCESS_KEY has been reduced from 0.8 to 0.45

  3. We have defined confidence score per entity

dristysrivastava and others added 5 commits August 7, 2024 15:42
* Adding confidence score to entities and topic responses

* Adding labels and fixing UTS

* Adding utils

* Fixing UT

* Remove unused imports

* Updating topic classifier

---------

Co-authored-by: dristy.cd <[email protected]>
@gr8nishan gr8nishan changed the base branch from main to pebblo-0.1.18 August 13, 2024 08:57
@gr8nishan gr8nishan changed the title Confidence score Confidence score changes in Entity Classifier Aug 13, 2024
pebblo/entity_classifier/utils/config.py Outdated Show resolved Hide resolved
pebblo/entity_classifier/entity_classifier.py Outdated Show resolved Hide resolved
pebblo/entity_classifier/utils/config.py Outdated Show resolved Hide resolved
pebblo/entity_classifier/utils/config.py Outdated Show resolved Hide resolved
@gr8nishan gr8nishan merged commit e4418f8 into daxa-ai:pebblo-0.1.18 Aug 13, 2024
15 checks passed
@gr8nishan gr8nishan deleted the confidence_score branch August 13, 2024 12:39
shreyas-damle pushed a commit that referenced this pull request Aug 21, 2024
* Adding confidence score to entities and topic responses (#460)

* Adding confidence score to entities and topic responses

* Adding labels and fixing UTS

* Adding utils

* Fixing UT

* Remove unused imports

* Updating topic classifier

---------

Co-authored-by: dristy.cd <[email protected]>

* Added changes for prompt group

* resolved linting issue

* added changes for confidence score for entity classification

* added changes for confidence score

* review comment changes

* review comment changes

* review comment changes

---------

Co-authored-by: Dristy Srivastava <[email protected]>
Co-authored-by: dristy.cd <[email protected]>
gr8nishan pushed a commit that referenced this pull request Aug 21, 2024
* Adding confidence score to entities and topic responses (#460)
* Changes for confidence score in /loader/doc as well as UI API (#470)
* Confidence score changes in Entity Classifier (#473)
* Confidence score UI (#480)

* Added changes for entity groups (#466) 
* Adding IP address in entity classifier (#466)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants