Support for improved LASER2 embeddings #45
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
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Outdated suggestions cannot be applied.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.
Hi,
in the current version of Facebook's LASER repository they provide an improved LASER2 model trained on the same languages as the original LASER model. However they also introduced a sentencepiece model (SPM) for Tokenization. So I made a few changes to your code such that one can use the improved model easily in Python. In order to ensure that it is working, I compared generated embeddings with original LASER2 embeddings (obtained by using a fork of your test data repository. The resulting report shows an almost perfect matching.
The tests for the new embeddings might still have to be adapted such that one can run them with poetry and pytest.
Feel free to check out the changes :)