Upgrade model training dependencies #42
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
The Ons tokenizer has a few tokenizer rules to accommodate some domain specific tokenization issues. We can re-use this tokenizer to not negatively impact the token-based evaluation
We add `()/` to accommodate some domain specific cases ways of writing
# Conflicts: # README.md
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Outdated suggestions cannot be applied.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 PR upgrades many dependencies of this project to the latest version (especially Flair, Torch and spaCy). All model were re-trained with the new code to ensure compatibility. On an entity-level, models perform equally, or better. On a token-level, effectiveness is slightly decreased (presumably due to suboptimal tokenization). This is an acceptable tradeoff for the newer and future-proof dependencies.
New models were released (see update in README).