org.deeplearning4j.models.word2vec

Class Word2Vec

java.lang.Object

org.deeplearning4j.models.word2vec.Word2Vec

All Implemented Interfaces:

Serializable, Persistable

public class Word2Vec
extends Object
implements Persistable

Leveraging a 3 layer neural net with a softmax approach as output, converts a word based on its context and the training examples in to a numeric vector

Author:

Adam Gibson

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	Word2Vec.Builder

Field Summary

Fields

Modifier and Type	Field and Description
static String	UNK

Constructor Summary

Constructors

Constructor and Description
Word2Vec()

Method Summary

Modifier and Type	Method and Description
TreeSet<VocabWord>	analogy(String word0, String word1, String word2)
List<String>	analogyWords(String w1, String w2, String w3) Brings back a list of words that are analagous to the 3 words presented in vector space
boolean	buildVocab() Builds the vocabulary for training
Set<VocabWord>	distance(String word)
void	fit() Train the model
VocabCache	getCache()
int	getLayerSize()
SentenceIterator	getSentenceIter()
List<String>	getStopWords()
TokenizerFactory	getTokenizerFactory()
int	getWindow()
double[]	getWordVector(String word) Get the word vector for a given matrix
org.nd4j.linalg.api.ndarray.INDArray	getWordVectorMatrix(String word) Get the word vector for a given matrix
org.nd4j.linalg.api.ndarray.INDArray	getWordVectorMatrixNormalized(String word) Returns the word vector divided by the norm2 of the array
boolean	hasWord(String word) Returns true if the model has this word in the vocab
int	indexOf(String word)
void	iterate(VocabWord w1, VocabWord w2, AtomicLong nextRandom) Train the word vector on the given words
void	load(InputStream is)
void	plotTsne() Create a tsne plot
void	setCache(VocabCache cache)
void	setLayerSize(int layerSize)
void	setSentenceIter(SentenceIterator sentenceIter) Note that calling a setter on this means assumes that this is a training continuation and therefore weights should not be reset.
void	setTokenizerFactory(TokenizerFactory tokenizerFactory)
void	setup()
double	similarity(String word, String word2) Returns the similarity of 2 words
List<String>	similarWordsInVocabTo(String word, double accuracy) Find all words with a similar characters in the vocab
void	skipGram(int i, List<VocabWord> sentence, int b, AtomicLong nextRandom) Train via skip gram
void	trainSentence(List<VocabWord> sentence, AtomicInteger numWordsSoFar, AtomicLong nextRandom) Train on a list of vocab words
Collection<String>	wordsNearest(String word, int n) Get the top n words most similar to the given word
void	write(OutputStream os)

Methods inherited from class java.lang.Object

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

Field Detail

UNK

public static final String UNK

See Also:

Constant Field Values

Constructor Detail

Word2Vec

public Word2Vec()

Method Detail

similarWordsInVocabTo

public List<String> similarWordsInVocabTo(String word,
                                          double accuracy)

Find all words with a similar characters in the vocab

Parameters:

word - the word to compare

accuracy - the accuracy: 0 to 1

Returns:

the list of words that are similar in the vocab

indexOf

public int indexOf(String word)

getWordVector

public double[] getWordVector(String word)

Get the word vector for a given matrix

Parameters:

word - the word to get the matrix for

Returns:

the ndarray for this word

getWordVectorMatrix

public org.nd4j.linalg.api.ndarray.INDArray getWordVectorMatrix(String word)

Get the word vector for a given matrix

Parameters:

word - the word to get the matrix for

Returns:

the ndarray for this word

getWordVectorMatrixNormalized

public org.nd4j.linalg.api.ndarray.INDArray getWordVectorMatrixNormalized(String word)

Returns the word vector divided by the norm2 of the array

Parameters:

word - the word to get the matrix for

Returns:

the looked up matrix

wordsNearest

public Collection<String> wordsNearest(String word,
                                       int n)

Get the top n words most similar to the given word

Parameters:

word - the word to compare

n - the n to get

Returns:

the top n words

analogyWords

public List<String> analogyWords(String w1,
                                 String w2,
                                 String w3)

Brings back a list of words that are analagous to the 3 words presented in vector space

Parameters:

w1 -

w2 -

w3 -

Returns:

a list of words that are an analogy for the given 3 words

hasWord

public boolean hasWord(String word)

Returns true if the model has this word in the vocab

Parameters:

word - the word to test for

Returns:

true if the model has the word in the vocab

fit

public void fit()

Train the model

distance

public Set<VocabWord> distance(String word)

Parameters:

word -

Returns:

analogy

public TreeSet<VocabWord> analogy(String word0,
                                  String word1,
                                  String word2)

Returns:

setup

public void setup()

buildVocab

public boolean buildVocab()

Builds the vocabulary for training

plotTsne

public void plotTsne()

Create a tsne plot

trainSentence

public void trainSentence(List<VocabWord> sentence,
                          AtomicInteger numWordsSoFar,
                          AtomicLong nextRandom)

Train on a list of vocab words

Parameters:

sentence - the list of vocab words to train on

skipGram

public void skipGram(int i,
                     List<VocabWord> sentence,
                     int b,
                     AtomicLong nextRandom)

Train via skip gram

Parameters:

i -

sentence -

iterate

public void iterate(VocabWord w1,
                    VocabWord w2,
                    AtomicLong nextRandom)

Train the word vector on the given words

Parameters:

w1 - the first word to fit

similarity

public double similarity(String word,
                         String word2)

Returns the similarity of 2 words

Parameters:

word - the first word

word2 - the second word

Returns:

a normalized similarity (cosine similarity)

write

public void write(OutputStream os)

Specified by:

write in interface Persistable

load

public void load(InputStream is)

Specified by:

load in interface Persistable

setSentenceIter

public void setSentenceIter(SentenceIterator sentenceIter)

Note that calling a setter on this means assumes that this is a training continuation and therefore weights should not be reset.

Parameters:

sentenceIter -

getLayerSize

public int getLayerSize()

setLayerSize

public void setLayerSize(int layerSize)

getWindow

public int getWindow()

getStopWords

public List<String> getStopWords()

getSentenceIter

public SentenceIterator getSentenceIter()

getTokenizerFactory

public TokenizerFactory getTokenizerFactory()

setTokenizerFactory

public void setTokenizerFactory(TokenizerFactory tokenizerFactory)

getCache

public VocabCache getCache()

setCache

public void setCache(VocabCache cache)