org.deeplearning4j.models.embeddings.reader

Interface ModelUtils<T extends SequenceElement>

All Known Implementing Classes:

BasicModelUtils, FlatModelUtils, TreeModelUtils

public interface ModelUtils<T extends SequenceElement>

Instances implementing this interface should be responsible for utility access to SequenceVectors model

Author:

[email protected]

Method Summary

Modifier and Type	Method and Description
Map<String,Double>	accuracy(List<String> questions) Accuracy based on questions which are a space separated list of strings where the first word is the query word, the next 2 words are negative, and the last word is the predicted word to be nearest
void	init(WeightLookupTable<T> lookupTable) This method implementations should accept given lookup table, and use them in further calls to interface methods
double	similarity(String label1, String label2) This method implementations should return distance between two given elements
List<String>	similarWordsInVocabTo(String word, double accuracy) Find all words with a similar characters in the vocab
Collection<String>	wordsNearest(Collection<String> positive, Collection<String> negative, int top) Words nearest based on positive and negative words
Collection<String>	wordsNearest(org.nd4j.linalg.api.ndarray.INDArray words, int top) Words nearest based on positive and negative words * @param top the top n words
Collection<String>	wordsNearest(String label, int n) This method implementations should return N nearest elements labels to given element's label
Collection<String>	wordsNearestSum(Collection<String> positive, Collection<String> negative, int top)
Collection<String>	wordsNearestSum(org.nd4j.linalg.api.ndarray.INDArray words, int top)
Collection<String>	wordsNearestSum(String word, int n)

Method Detail

init

void init(WeightLookupTable<T> lookupTable)

This method implementations should accept given lookup table, and use them in further calls to interface methods

Parameters:

lookupTable -

similarity

double similarity(String label1,
                  String label2)

This method implementations should return distance between two given elements

Parameters:

label1 -

label2 -

Returns:

accuracy

Map<String,Double> accuracy(List<String> questions)

Accuracy based on questions which are a space separated list of strings where the first word is the query word, the next 2 words are negative, and the last word is the predicted word to be nearest

Parameters:

questions - the questions to ask

Returns:

the accuracy based on these questions

similarWordsInVocabTo

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

wordsNearest

Collection<String> wordsNearest(String label,
                                int n)

This method implementations should return N nearest elements labels to given element's label

Parameters:

label - label to return nearest elements for

n - number of nearest words to return

Returns:

wordsNearest

Collection<String> wordsNearest(Collection<String> positive,
                                Collection<String> negative,
                                int top)

Words nearest based on positive and negative words

Parameters:

positive - the positive words

negative - the negative words

top - the top n words

Returns:

the words nearest the mean of the words

wordsNearest

Collection<String> wordsNearest(org.nd4j.linalg.api.ndarray.INDArray words,
                                int top)

Words nearest based on positive and negative words * @param top the top n words

Returns:

the words nearest the mean of the words

wordsNearestSum

Collection<String> wordsNearestSum(String word,
                                   int n)

wordsNearestSum

Collection<String> wordsNearestSum(org.nd4j.linalg.api.ndarray.INDArray words,
                                   int top)

wordsNearestSum

Collection<String> wordsNearestSum(Collection<String> positive,
                                   Collection<String> negative,
                                   int top)