sentence embeddings with Sbert. #1405
Merged
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
There was a problem hiding this comment.
This looks like an awesome example! Just filled in a few preliminary nitpicks after a quick first-pass on the content for this tutorial. I guess you may have to do a bit of a grammar check in-place to get things right, but the concepts look good to me!
Some high-level comments though, which are kinda repeated across the tutorial
- Make sure you remove all the
<br>tags, they don't need to be added explicitly - Make sure your links are all on the same lines, don't break them
- Some places require capitalization. I think putting the text through a grammar checker should remove those errors fairly quickly
Thanks for this, I'm sure folks would love it! Delegating the rest to the able hands of @mattdangerw of course!
Grammar fix
|
@suvadityamuk Thanks! |
mattdangerw
requested changes
Jun 27, 2023
fchollet
reviewed
Jul 12, 2023
|
@fchollet I have just pushed the generated files. |
|
Thank you for the great contribution! |
|
@fchollet You are welcome |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in 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Outdated suggestions cannot be applied.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.
this is an example of how to use RoBERTa from keras-nlp in another model and fine-tune it using siamese networks for semantic similarity tasks.
I fine tuned the model with two methods (regression objective and triplet objective).
the paper that this example is based on is sbert
here is a colab gist with the code.