| Package | Description |
|---|---|
| org.deeplearning4j.text.tokenization.tokenizer | |
| org.deeplearning4j.text.tokenization.tokenizerfactory |
| Modifier and Type | Class and Description |
|---|---|
class |
BertWordPieceStreamTokenizer |
class |
BertWordPieceTokenizer |
class |
DefaultStreamTokenizer
Tokenizer based on the
StreamTokenizer |
class |
DefaultTokenizer
Default tokenizer
|
class |
NGramTokenizer |
| Constructor and Description |
|---|
NGramTokenizer(Tokenizer tokenizer,
Integer minN,
Integer maxN) |
| Modifier and Type | Method and Description |
|---|---|
Tokenizer |
BertWordPieceTokenizerFactory.create(InputStream toTokenize) |
Tokenizer |
TokenizerFactory.create(InputStream toTokenize)
Create a tokenizer based on an input stream
|
Tokenizer |
NGramTokenizerFactory.create(InputStream toTokenize) |
Tokenizer |
DefaultTokenizerFactory.create(InputStream toTokenize) |
Tokenizer |
BertWordPieceTokenizerFactory.create(String toTokenize) |
Tokenizer |
TokenizerFactory.create(String toTokenize)
The tokenizer to createComplex
|
Tokenizer |
NGramTokenizerFactory.create(String toTokenize) |
Tokenizer |
DefaultTokenizerFactory.create(String toTokenize) |
Copyright © 2021. All rights reserved.