org.deeplearning4j.models.paragraphvectors

Class ParagraphVectors

java.lang.Object

org.deeplearning4j.models.embeddings.wordvectors.WordVectorsImpl<T>

org.deeplearning4j.models.sequencevectors.SequenceVectors<VocabWord>

org.deeplearning4j.models.word2vec.Word2Vec

org.deeplearning4j.models.paragraphvectors.ParagraphVectors

All Implemented Interfaces:

Serializable, WordVectors

public class ParagraphVectors
extends Word2Vec

Basic ParagraphVectors (aka Doc2Vec) implementation for DL4j, as wrapper over SequenceVectors

Author:

[email protected]

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ParagraphVectors.Builder

Nested classes/interfaces inherited from class org.deeplearning4j.models.sequencevectors.SequenceVectors

SequenceVectors.AsyncSequencer

Field Summary

Fields

Modifier and Type	Field and Description
protected LabelAwareIterator	labelAwareIterator
protected List<VocabWord>	labelsList
protected org.nd4j.linalg.api.ndarray.INDArray	labelsMatrix
protected LabelsSource	labelsSource
protected boolean	normalizedLabels

Fields inherited from class org.deeplearning4j.models.word2vec.Word2Vec

sentenceIter, tokenizerFactory

Fields inherited from class org.deeplearning4j.models.sequencevectors.SequenceVectors

configuration, configured, elementsLearningAlgorithm, eventListeners, existingModel, iterator, log, scoreElements, scoreSequences, sequenceLearningAlgorithm, unknownElement

Fields inherited from class org.deeplearning4j.models.embeddings.wordvectors.WordVectorsImpl

batchSize, DEFAULT_UNK, layerSize, learningRate, learningRateDecayWords, lookupTable, minLearningRate, minWordFrequency, modelUtils, negative, numEpochs, numIterations, resetModel, sampling, seed, stopWords, trainElementsVectors, trainSequenceVectors, useAdeGrad, useUnknown, variableWindows, vocab, window, workers

Constructor Summary

Constructors

Constructor and Description
ParagraphVectors()

Method Summary

Modifier and Type	Method and Description
void	extractLabels()
void	fit() Starts training over
org.nd4j.linalg.api.ndarray.INDArray	inferVector(LabelledDocument document) This method calculates inferred vector for given document, with default parameters for learning rate and iterations
org.nd4j.linalg.api.ndarray.INDArray	inferVector(LabelledDocument document, double learningRate, double minLearningRate, int iterations) This method calculates inferred vector for given document
org.nd4j.linalg.api.ndarray.INDArray	inferVector(List<VocabWord> document) This method calculates inferred vector for given list of words, with default parameters for learning rate and iterations
org.nd4j.linalg.api.ndarray.INDArray	inferVector(List<VocabWord> document, double learningRate, double minLearningRate, int iterations) This method calculates inferred vector for given document
org.nd4j.linalg.api.ndarray.INDArray	inferVector(String text) This method calculates inferred vector for given text, with default parameters for learning rate and iterations
org.nd4j.linalg.api.ndarray.INDArray	inferVector(String text, double learningRate, double minLearningRate, int iterations) This method calculates inferred vector for given text
Collection<String>	nearestLabels(Collection<VocabWord> document, int topN) This method returns top N labels nearest to specified set of vocab words
Collection<String>	nearestLabels(org.nd4j.linalg.api.ndarray.INDArray labelVector, int topN) This method returns top N labels nearest to specified features vector
Collection<String>	nearestLabels(LabelledDocument document, int topN) This method returns top N labels nearest to specified document
Collection<String>	nearestLabels(String rawText, int topN) This method returns top N labels nearest to specified text
String	predict(LabelledDocument document) Deprecated.
String	predict(List<VocabWord> document) Deprecated.
String	predict(String rawText) Deprecated.
Collection<String>	predictSeveral(LabelledDocument document, int limit) Deprecated.
Collection<String>	predictSeveral(List<VocabWord> document, int limit) Deprecated.
Collection<String>	predictSeveral(String rawText, int limit) Deprecated.
double	similarityToLabel(LabelledDocument document, String label) Deprecated.
double	similarityToLabel(List<VocabWord> document, String label) Deprecated.
double	similarityToLabel(String rawText, String label) Deprecated.

Methods inherited from class org.deeplearning4j.models.word2vec.Word2Vec

setSentenceIter, setTokenizerFactory

Methods inherited from class org.deeplearning4j.models.sequencevectors.SequenceVectors

buildVocab, getElementsScore, getSequencesScore, initLearners, trainSequence

Methods inherited from class org.deeplearning4j.models.embeddings.wordvectors.WordVectorsImpl

accuracy, getLayerSize, getWordVector, getWordVectorMatrix, getWordVectorMatrixNormalized, getWordVectors, getWordVectorsMean, hasWord, indexOf, lookupTable, setLookupTable, setModelUtils, setVocab, similarity, similarWordsInVocabTo, update, update, vocab, wordsNearest, wordsNearest, wordsNearest, wordsNearestSum, wordsNearestSum, wordsNearestSum

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.deeplearning4j.models.embeddings.wordvectors.WordVectors

accuracy, getUNK, getWordVector, getWordVectorMatrix, getWordVectorMatrixNormalized, getWordVectors, getWordVectorsMean, hasWord, indexOf, lookupTable, setModelUtils, setUNK, similarity, similarWordsInVocabTo, vocab, wordsNearest, wordsNearest, wordsNearest, wordsNearestSum, wordsNearestSum, wordsNearestSum

Field Detail

labelsSource

protected LabelsSource labelsSource

labelAwareIterator

protected transient LabelAwareIterator labelAwareIterator

labelsMatrix

protected org.nd4j.linalg.api.ndarray.INDArray labelsMatrix

labelsList

protected List<VocabWord> labelsList

normalizedLabels

protected boolean normalizedLabels

Constructor Detail

ParagraphVectors

public ParagraphVectors()

Method Detail

predict

@Deprecated
public String predict(String rawText)

Deprecated.

This method takes raw text, applies tokenizer, and returns most probable label

Parameters:

rawText -

Returns:

predict

@Deprecated
public String predict(LabelledDocument document)

Deprecated.

This method predicts label of the document. Computes a similarity wrt the mean of the representation of words in the document

Parameters:

document - the document

Returns:

the word distances for each label

extractLabels

public void extractLabels()

inferVector

public org.nd4j.linalg.api.ndarray.INDArray inferVector(String text,
                                                        double learningRate,
                                                        double minLearningRate,
                                                        int iterations)

This method calculates inferred vector for given text

Parameters:

text -

Returns:

inferVector

public org.nd4j.linalg.api.ndarray.INDArray inferVector(LabelledDocument document,
                                                        double learningRate,
                                                        double minLearningRate,
                                                        int iterations)

This method calculates inferred vector for given document

Parameters:

document -

Returns:

inferVector

public org.nd4j.linalg.api.ndarray.INDArray inferVector(List<VocabWord> document,
                                                        double learningRate,
                                                        double minLearningRate,
                                                        int iterations)

This method calculates inferred vector for given document

Parameters:

document -

Returns:

inferVector

public org.nd4j.linalg.api.ndarray.INDArray inferVector(String text)

This method calculates inferred vector for given text, with default parameters for learning rate and iterations

Parameters:

text -

Returns:

inferVector

public org.nd4j.linalg.api.ndarray.INDArray inferVector(LabelledDocument document)

This method calculates inferred vector for given document, with default parameters for learning rate and iterations

Parameters:

document -

Returns:

inferVector

public org.nd4j.linalg.api.ndarray.INDArray inferVector(List<VocabWord> document)

This method calculates inferred vector for given list of words, with default parameters for learning rate and iterations

Parameters:

document -

Returns:

predict

@Deprecated
public String predict(List<VocabWord> document)

Deprecated.

This method predicts label of the document. Computes a similarity wrt the mean of the representation of words in the document

Parameters:

document - the document

Returns:

the word distances for each label

predictSeveral

@Deprecated
public Collection<String> predictSeveral(@NonNull
                                                     LabelledDocument document,
                                                     int limit)

Deprecated.

Predict several labels based on the document. Computes a similarity wrt the mean of the representation of words in the document

Parameters:

document - raw text of the document

Returns:

possible labels in descending order

predictSeveral

@Deprecated
public Collection<String> predictSeveral(String rawText,
                                                     int limit)

Deprecated.

Predict several labels based on the document. Computes a similarity wrt the mean of the representation of words in the document

Parameters:

rawText - raw text of the document

Returns:

possible labels in descending order

predictSeveral

@Deprecated
public Collection<String> predictSeveral(List<VocabWord> document,
                                                     int limit)

Deprecated.

Predict several labels based on the document. Computes a similarity wrt the mean of the representation of words in the document

Parameters:

document - the document

Returns:

possible labels in descending order

nearestLabels

public Collection<String> nearestLabels(LabelledDocument document,
                                        int topN)

This method returns top N labels nearest to specified document

Parameters:

document -

topN -

Returns:

nearestLabels

public Collection<String> nearestLabels(String rawText,
                                        int topN)

This method returns top N labels nearest to specified text

Parameters:

rawText -

topN -

Returns:

nearestLabels

public Collection<String> nearestLabels(Collection<VocabWord> document,
                                        int topN)

This method returns top N labels nearest to specified set of vocab words

Parameters:

document -

topN -

Returns:

nearestLabels

public Collection<String> nearestLabels(org.nd4j.linalg.api.ndarray.INDArray labelVector,
                                        int topN)

This method returns top N labels nearest to specified features vector

Parameters:

labelVector -

topN -

Returns:

similarityToLabel

@Deprecated
public double similarityToLabel(String rawText,
                                            String label)

Deprecated.

This method returns similarity of the document to specific label, based on mean value

Parameters:

rawText -

label -

Returns:

fit

public void fit()

Description copied from class: SequenceVectors

Starts training over

Overrides:

fit in class SequenceVectors<VocabWord>

similarityToLabel

@Deprecated
public double similarityToLabel(LabelledDocument document,
                                            String label)

Deprecated.

This method returns similarity of the document to specific label, based on mean value

Parameters:

document -

label -

Returns:

similarityToLabel

@Deprecated
public double similarityToLabel(List<VocabWord> document,
                                            String label)

Deprecated.

This method returns similarity of the document to specific label, based on mean value

Parameters:

document -

label -

Returns: