nlp/com.londogard.nlp.embeddings/WordEmbeddings

WordEmbeddings

public final class WordEmbeddings implements Embeddings

Ordinary Word Embeddings.

Constructors

public WordEmbeddings WordEmbeddings( Path filePath, Integer dimensions, Character delimiter)

Types

public class Companion

Functions

public final List<Pair<String, Float>> analogy( String w1, String w2, String w3, Integer N)

Find the N closest terms in the vocab to the analogy:

public Boolean contains(String word)

Check if the word has an embedding.

public Float cosineDistance(String w1, String w2)

public final List<Pair<String, Float>> distance(List<String> input, Integer N)

Find the N closest terms in the vocab to the input word(s).

euclideanDistance

public Float euclideanDistance(String w1, String w2)

public Character getDelimiter()

public Integer getDimensions()

public Map<String, NDArray<Float, D1>> getEmbeddings()

Vocabulary, word to embedded space

public Path getFilePath()

public Set<String> getVocabulary()

nearestNeighbours

public final List<Pair<String, Float>> nearestNeighbours( NDArray<Float, D1> vector, Set<String> inSet, Set<String> outSet, Integer N)

Find N closest terms in the vocab to the given vector, using only words from the in-set (if defined) and excluding all words from the out-set (if non-empty). Although you can, it doesn't make much sense to define both in and out sets.

public final List<Pair<String, Float>> rank(String word, Set<String> set)

Rank a set of words by their respective distance to some central term.

traverseVectors

public List<NDArray<Float, D1>> traverseVectors(List<String> words)

traverseVectorsOrNull

public List<NDArray<Float, D1>> traverseVectorsOrNull(List<String> words)

public NDArray<Float, D1> vector(String word)

Fetches Embedding if it exists for word

Properties

private final Character delimiter

private final Integer dimensions

private final Map<String, NDArray<Float, D1>> embeddings

Vocabulary, word to embedded space

private final Path filePath

private final Set<String> vocabulary