Add Tokenizer Helper class to ERNIE-Bot.SDK #61
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
Add a new Tokenizer class in the ERNIE-Bot.SDK namespace that provides methods for tokenizing text. The class includes a method, ApproxNumTokens, which calculates the approximate number of tokens in a given text. The method counts the number of Han characters and estimates the number of words based on whitespace. The result is the sum of the Han character count and 1.3 times the word count. The class also includes a unit test for the ApproxNumTokens method.
- Improve accuracy of token counting in ApproxNumTokens method - Count Chinese characters using regular expression - Count English words excluding special characters - Adjust token count based on English word count - Update unit tests to reflect changes in token counting logic
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Outdated suggestions cannot be applied.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.
Summary:
This pull request adds a new Tokenizer class to the ERNIE-Bot.SDK project. The Tokenizer class provides methods for tokenizing text. It includes a method called
ApproxNumTokens, which calculates an approximate number of tokens in a given text. The method takes into account whitespace, Chinese characters, and other letters. The Tokenizer
class is a static class and can be used directly without instantiation.
Changes:
and other letters.