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

[ENH] Document Embedding: add SBERT #839

Merged
merged 4 commits into from
Jun 30, 2022

Conversation

djukicn
Copy link
Collaborator

@djukicn djukicn commented Apr 27, 2022

Issue

Implements #639.

Description of changes

Added multilingual SBERT into Document Embedding widget.

Includes
  • Code changes
  • Tests
  • Documentation

@codecov-commenter
Copy link

codecov-commenter commented Apr 27, 2022

Codecov Report

Merging #839 (170cd4c) into master (7f3baed) will increase coverage by 0.03%.
The diff coverage is 88.46%.

@@            Coverage Diff             @@
##           master     #839      +/-   ##
==========================================
+ Coverage   76.92%   76.96%   +0.03%     
==========================================
  Files          85       85              
  Lines       11966    11950      -16     
  Branches     1880     1877       -3     
==========================================
- Hits         9205     9197       -8     
+ Misses       2454     2449       -5     
+ Partials      307      304       -3     

@PrimozGodec PrimozGodec self-requested a review May 6, 2022 07:02
@PrimozGodec PrimozGodec self-assigned this May 6, 2022
Copy link
Collaborator

@PrimozGodec PrimozGodec left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for implementing it looks good. I just dropped a few minor comments.
Please also rebase this PR to master (sorry I was changing callbacks already since I didn't notice that you have been changing that here).

Before it can get merged we need to add GPU sbert embedders to the server. Hope it will be done soon. :)

orangecontrib/text/vectorization/sbert.py Outdated Show resolved Hide resolved
orangecontrib/text/vectorization/sbert.py Outdated Show resolved Hide resolved
orangecontrib/text/vectorization/sbert.py Outdated Show resolved Hide resolved
orangecontrib/text/widgets/owdocumentembedding.py Outdated Show resolved Hide resolved
@djukicn djukicn force-pushed the document-embedding-add-sbert branch 2 times, most recently from 402e42c to 76457e2 Compare May 19, 2022 15:51
@PrimozGodec PrimozGodec force-pushed the document-embedding-add-sbert branch from 76457e2 to b67016c Compare June 29, 2022 13:05
@PrimozGodec PrimozGodec force-pushed the document-embedding-add-sbert branch from b67016c to 9df9fff Compare June 29, 2022 14:02
@PrimozGodec PrimozGodec force-pushed the document-embedding-add-sbert branch from 9df9fff to 170cd4c Compare June 29, 2022 14:20
@PrimozGodec PrimozGodec changed the title Document Embedding: add SBERT [ENH] Document Embedding: add SBERT Jun 30, 2022
@djukicn djukicn merged commit be87655 into biolab:master Jun 30, 2022
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