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 LabelsSource	labelsSource

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

sentenceIter, tokenizerFactory

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

configuration, elementsLearningAlgorithm, iterator, log, sequenceLearningAlgorithm

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

batchSize, layerSize, learningRate, learningRateDecayWords, lookupTable, minLearningRate, minWordFrequency, negative, numEpochs, numIterations, resetModel, sampling, stopWords, trainElementsVectors, trainSequenceVectors, UNK, useAdeGrad, vocab, vpTree, window, workers

Constructor Summary

Constructors

Constructor and Description
ParagraphVectors()

Method Summary

Modifier and Type	Method and Description
String	predict(List<VocabWord> document) Predict several based on the document.
Counter<String>	predictSeveral(List<VocabWord> document) Predict several based on the document.

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

setSentenceIter

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

buildVocab, fit, trainSequence

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

accuracy, getWordVector, getWordVectorMatrix, getWordVectorMatrixNormalized, hasWord, indexOf, lookupTable, setLookupTable, setVocab, similarity, similarWordsInVocabTo, vocab, wordsNearest, 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, getWordVector, getWordVectorMatrix, getWordVectorMatrixNormalized, hasWord, indexOf, lookupTable, similarity, similarWordsInVocabTo, vocab, wordsNearest, wordsNearest, wordsNearest, wordsNearestSum, wordsNearestSum, wordsNearestSum

Field Detail

labelsSource

protected LabelsSource labelsSource

labelAwareIterator

protected LabelAwareIterator labelAwareIterator

Constructor Detail

ParagraphVectors

public ParagraphVectors()

Method Detail

predict

public String predict(List<VocabWord> document)

Predict several based on 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

public Counter<String> predictSeveral(List<VocabWord> document)

Predict several based on 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