ai.djl.modality.nlp.bert

Class WordpieceTokenizer

java.lang.Object

ai.djl.modality.nlp.preprocess.SimpleTokenizer

ai.djl.modality.nlp.bert.WordpieceTokenizer

All Implemented Interfaces:

TextProcessor, Tokenizer

public class WordpieceTokenizer
extends SimpleTokenizer

WordpieceTokenizer tokenizes a piece of text into its word pieces.

This uses a greedy longest-match-first algorithm to perform tokenization using the given vocabulary. The input text should already be cleaned and preprocessed.

 jshell> String input = "unaffable";
 jshell> wordpieceTokenizer.tokenize(intput);
 ["un", "##aff", "##able"]
 

Reference implementation: Google Research Bert Tokenizer

Constructor Summary

Constructors

Constructor and Description
WordpieceTokenizer(DefaultVocabulary vocabulary, java.lang.String unknown, int maxInputChars) Creates an instance of WordpieceTokenizer.

Method Summary

Modifier and Type	Method and Description
java.util.List<java.lang.String>	tokenize(java.lang.String sentence) Breaks down the given sentence into a list of tokens that can be represented by embeddings.

Methods inherited from class ai.djl.modality.nlp.preprocess.SimpleTokenizer

buildSentence

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface ai.djl.modality.nlp.preprocess.Tokenizer

preprocess

Constructor Detail

WordpieceTokenizer

public WordpieceTokenizer(DefaultVocabulary vocabulary,
                          java.lang.String unknown,
                          int maxInputChars)

Creates an instance of WordpieceTokenizer.

Parameters:

vocabulary - a DefaultVocabulary used for wordpiece tokenization

unknown - String that represent unknown token

maxInputChars - maximum number of input characters

Method Detail

tokenize

public java.util.List<java.lang.String> tokenize(java.lang.String sentence)

Breaks down the given sentence into a list of tokens that can be represented by embeddings.

Specified by:

tokenize in interface Tokenizer

Overrides:

tokenize in class SimpleTokenizer

Parameters:

sentence - the sentence to tokenize

Returns:

a List of tokens