Load a pretrained word embedding using fastTextWordEmbedding. This function requires Text Analytics Toolbox™ Model for fastText English 16 Billion Token Word Embedding support package. If this support package is not installed, then the function provides a download link.

emb = fastTextWordEmbedding

emb = 
  wordEmbedding with properties:

     Dimension: 300
    Vocabulary: [1×1000000 string]

Map the words "Italy", "Rome", and "Paris" to vectors using word2vec.

italy = word2vec(emb,"Italy");
rome = word2vec(emb,"Rome");
paris = word2vec(emb,"Paris");

Map the vector italy - rome + paris to a word using vec2word.

word = vec2word(emb,italy - rome + paris)

word = 
"France"

Find the top five closest words to a word embedding vector and their distances.

Load a pretrained word embedding using fastTextWordEmbedding. This function requires Text Analytics Toolbox™ Model for fastText English 16 Billion Token Word Embedding support package. If this support package is not installed, then the function provides a download link.

emb = fastTextWordEmbedding;

Map the words "Italy", "Rome", and "Paris" to vectors using word2vec.

italy = word2vec(emb,"Italy");
rome = word2vec(emb,"Rome");
paris = word2vec(emb,"Paris");

Map the vector italy - rome + paris to a word using vec2word. Find the top five closest words using the Euclidean distance metric.

k = 5;
M = italy - rome + paris;
[words,dist] = vec2word(emb,M,k,'Distance','euclidean');

Plot the words and distances in a bar chart.

figure;
bar(dist)
xticklabels(words)
xlabel("Word")
ylabel("Distance")
title("Distances to Vector")