Package ai.djl.modality.nlp.bert

Class BertTokenizer

java.lang.Object

ai.djl.modality.nlp.preprocess.SimpleTokenizer

ai.djl.modality.nlp.bert.BertTokenizer

All Implemented Interfaces:

TextProcessor, Tokenizer

Direct Known Subclasses:

BertFullTokenizer

public class BertTokenizer
extends SimpleTokenizer

BertTokenizer is a class to help you encode question and paragraph sentence.

Constructor Summary

Constructors

Constructor	Description
BertTokenizer()

Method Summary

Modifier and Type	Method	Description
BertToken	encode(java.lang.String question, java.lang.String paragraph)	Encodes questions and paragraph sentences.
BertToken	encode(java.lang.String question, java.lang.String paragraph, int maxLength)	Encodes questions and paragraph sentences with max length.
<E> java.util.List<E>	pad(java.util.List<E> tokens, E padItem, int num)	Pads the tokens to the required length.
java.util.List<java.lang.String>	tokenize(java.lang.String input)	Breaks down the given sentence into a list of tokens that can be represented by embeddings.
java.lang.String	tokenToString(java.util.List<java.lang.String> tokens)	Returns a string presentation of the tokens.

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

BertTokenizer

public BertTokenizer()

Method Detail

tokenize

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

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:

input - the sentence to tokenize

Returns:

a List of tokens

tokenToString

public java.lang.String tokenToString(java.util.List<java.lang.String> tokens)

Returns a string presentation of the tokens.

Parameters:

tokens - a list of tokens

Returns:

a string presentation of the tokens

pad

public <E> java.util.List<E> pad(java.util.List<E> tokens,
                                 E padItem,
                                 int num)

Pads the tokens to the required length.

Type Parameters:

E - the type of the List

Parameters:

tokens - the input tokens

padItem - the things to pad at the end

num - the total length after padding

Returns:

a list of padded tokens

encode

public BertToken encode(java.lang.String question,
                        java.lang.String paragraph)

Encodes questions and paragraph sentences.

Parameters:

question - the input question

paragraph - the input paragraph

Returns:

BertToken

encode

public BertToken encode(java.lang.String question,
                        java.lang.String paragraph,
                        int maxLength)

Encodes questions and paragraph sentences with max length.

Parameters:

question - the input question

paragraph - the input paragraph

maxLength - the maxLength

Returns:

BertToken