Advanced tokenization #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
leod
pushed a commit
to leod/OpenNMT-tf
that referenced
this pull request
Jun 3, 2023
* Add the OpenNMT tokenizer as a third party * Add detokenization logic * Add learn_bpe.py script * Replace spaces in CharacterTokenizer * Fix encoding issue when redirecting tokenization output * Move stream tokenization to the library * Build tokenizer plugin in Travis * Add BLEU evaluator variant which applies a light tokenization * Cleanup * Add documentation * Fix link * Complete the README * Fix tokenization configuration loading * Add missing instruction
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Outdated suggestions cannot be applied.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 adds advanced tokenization by using OpenNMT's Tokenizer as a plugin. It also adds the detokenization logic when saving inference or evaluation predictions.
Closes #24.