Skip to content

Add a SentencePiece tokenizer layer #27

@mattdangerw

Description

@mattdangerw

After landing the WordPiece tokenizer (#22) and hammering out a layerized tokenizer design, we should also support for SentencePiece tokenization. SentencePiece is both language agnostic and reversible, and will be an important addition to our tokenization offering. SentencePiece graph ops are already supported by tensorflow text.

Metadata

Metadata

Assignees

Labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions