neuralmonkey.util.word2vec module

Word2vec plug-in module.

This module provides functionality needed to work with word2vec files.

class neuralmonkey.util.word2vec.Word2Vec(path: str, encoding: str = 'utf-8') → None

Bases: object

__init__(path: str, encoding: str = 'utf-8') → None

Load the word2vec file.

embeddings

Get the embedding matrix.

vocabulary

Get a vocabulary object generated from this word2vec instance.

neuralmonkey.util.word2vec.get_word2vec_initializer(w2v: neuralmonkey.util.word2vec.Word2Vec) → Callable

Create a word2vec initializer.

A higher-order function that can be called from configuration.

neuralmonkey.util.word2vec.word2vec_vocabulary(w2v: neuralmonkey.util.word2vec.Word2Vec) → neuralmonkey.vocabulary.Vocabulary

Return the vocabulary from a word2vec object.

This is a helper method used from configuration.