Package smile.nlp.embedding

Class GloVe

java.lang.Object
smile.nlp.embedding.GloVe
public class GloVe extends Object
Global Vectors for Word Representation. GloVe is an unsupervised learning algorithm for obtaining vector representations for words.

GloVe is essentially a log-bilinear model with a weighted least-squares objective. The main intuition underlying the model is the simple observation that ratios of word-word co-occurrence probabilities have the potential for encoding some form of meaning.

Training is performed on aggregated global word-word co-occurrence statistics from a corpus. The training objective of GloVe is to learn word vectors such that their dot product equals the logarithm of the words' probability of co-occurrence. Owing to the fact that the logarithm of a ratio equals the difference of logarithms, this objective associates (the logarithm of) ratios of co-occurrence probabilities with vector differences in the word vector space. Because these ratios can encode some form of meaning, this information gets encoded as vector differences as well.

  • Constructor Details

    • GloVe

      public GloVe()

  • Method Details

    • of

      public static Word2Vec of(Path file) throws IOException
      Loads a GloVe model.
      Parameters:
      file - the path to model file.
      Returns:
      the GloVe model.
      Throws:
      IOException - when fails to read the file.