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

BertTokenizer may not be optimal choice for converstion #10

Open
MarkusSagen opened this issue Mar 12, 2022 · 0 comments
Open

BertTokenizer may not be optimal choice for converstion #10

MarkusSagen opened this issue Mar 12, 2022 · 0 comments
Labels
bug Something isn't working enhancement New feature or request

Comments

@MarkusSagen
Copy link
Collaborator

MarkusSagen commented Mar 12, 2022

Tensorflow supports two (or three) different types of WordPiece tokenizers.
Could be worth testing to use the FastWordPiece tokenizer, since it can build the model from a vocab directly and claims to be faster as mentioned:

But is will likely also require a bit more setup (https://www.tensorflow.org/text/guide/subwords_tokenizer#overview), as WordPiece only see to split words, but the BertTokenizer splits sentences

Goal

  • Compare the different tokenizers and see if they yield the same results
  • Compare if the new tokenizer can be saved as a Reusable SavedModel
  • Test if the models that previously fails now work Tokenizers do not convert tokens correctly #4
@MarkusSagen MarkusSagen added bug Something isn't working enhancement New feature or request labels Mar 12, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

1 participant