Wordpiece tokenizer #111
Merged
Wordpiece tokenizer #111
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
and WordpiecePreprocessTokenizer
replace tabs with spaces updated tests - all passing now. WordpiecePreprocessTokenizer is configurable. Added config param 'tokenizeChineseChars'
Craigacp
requested changes
Feb 2, 2021
Util/Tokenization/src/main/java/org/tribuo/util/tokens/Token.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/SplitCharactersTokenizer.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/SplitCharactersTokenizer.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/SplitCharactersTokenizer.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/SplitFunctionTokenizer.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/test/java/org/tribuo/util/tokens/impl/WhitespaceTokenizerTest.java
Show resolved
Hide resolved
...Tokenization/src/test/java/org/tribuo/util/tokens/impl/WordpiecePreprocessTokenizerTest.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/test/java/org/tribuo/util/tokens/impl/WordpieceTokenizerTest.java
Show resolved
Hide resolved
Util/Tokenization/src/test/java/org/tribuo/util/tokens/impl/WordpieceTokenizerTest.java
Outdated
Show resolved
Hide resolved
.../test/resources/org/tribuo/util/tokens/impl/test/regression-text_bert-base-uncased_fails.txt
Show resolved
Hide resolved
- additionally, fixed an issue with the neverSplit strings. - copyrights, javadocs, config params, etc.
Craigacp
requested changes
Feb 3, 2021
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/SplitCharactersTokenizer.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/wordpiece/WordpieceTokenizer.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/wordpiece/WordpieceTokenizer.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/wordpiece/WordpieceTokenizer.java
Outdated
Show resolved
Hide resolved
Util/Tokenization/src/main/java/org/tribuo/util/tokens/impl/wordpiece/WordpieceTokenizer.java
Show resolved
Hide resolved
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.
Description
An implementation of the Wordpiece tokenizer that is consistent with Huggingface implementation.
Motivation
This is useful for tokenizing text in Java so that we can have word ids that are consistent with BERT models built using Wordpiece-built vocabularies.