text2vec (version 0.5.0)

GlobalVectors: Creates Global Vectors word-embeddings model.

Description

Class for GloVe word-embeddings model. It can be trained via fully can asynchronous and parallel AdaGrad with $fit_transform() method.

Usage

GloVe

Format

R6Class object.

Fields

components

represents context word vectors

n_dump_every

integer = 0L by default. Defines frequency of dumping word vectors. For example user can ask to dump word vectors each 5 iteration.

shuffle

logical = FALSE by default. Defines shuffling before each SGD iteration. Generally shuffling is a good idea for stochastic-gradient descent, but from my experience in this particular case it does not improve convergence.

grain_size

integer = 1e5L by default. This is the grain_size for RcppParallel::parallelReduce. For details, see http://rcppcore.github.io/RcppParallel/#grain-size. We don't recommend to change this parameter.

Usage

For usage details see Methods, Arguments and Examples sections.

glove = GlobalVectors$new(word_vectors_size, vocabulary, x_max, learning_rate = 0.15,
                          alpha = 0.75, lambda = 0.0, shuffle = FALSE, initial = NULL)
glove$fit_transform(x, n_iter = 10L, convergence_tol = -1, n_check_convergence = 1L,
              n_threads = RcppParallel::defaultNumThreads(), ...)
glove$components
glove$dump()

Methods

$new(word_vectors_size, vocabulary, x_max, learning_rate = 0.15, alpha = 0.75, lambda = 0, shuffle = FALSE, initial = NULL)

Constructor for Global vectors model. For description of arguments see Arguments section.

$fit_transform(x, n_iter = 10L, convergence_tol = -1, n_check_convergence = 1L, n_threads = RcppParallel::defaultNumThreads(), ...)

fit Glove model to input matrix x

$dump()

get model internals - word vectors and biases for main and context words

$get_history

get history of SGD costs and word vectors (if n_dump_every > 0)

Arguments

glove

A GloVe object

x

An input term co-occurence matrix. Preferably in dgTMatrix format

n_iter

integer number of SGD iterations

word_vectors_size

desired dimension for word vectors

vocabulary

character vector or instance of text2vec_vocabulary class. Each word should correspond to dimension of co-occurence matrix.

x_max

integer maximum number of co-occurrences to use in the weighting function. see the GloVe paper for details: http://nlp.stanford.edu/pubs/glove.pdf

learning_rate

numeric learning rate for SGD. I do not recommend that you modify this parameter, since AdaGrad will quickly adjust it to optimal

convergence_tol

numeric = -1 defines early stopping strategy. We stop fitting when one of two following conditions will be satisfied: (a) we have used all iterations, or (b) cost_previous_iter / cost_current_iter - 1 < convergence_tol. By default perform all iterations.

alpha

numeric = 0.75 the alpha in weighting function formula : \(f(x) = 1 if x > x_max; else (x/x_max)^alpha\)

lambda

numeric = 0.0, L1 regularization coefficient. 0 = vanilla GloVe, corresponds to original paper and implementation. lambda >0 corresponds to text2vec new feature and different SGD algorithm. From our experience small lambda (like lambda = 1e-5) usually produces better results that vanilla GloVe on small corpuses

initial

NULL - word vectors and word biases will be initialized randomly. Or named list which contains w_i, w_j, b_i, b_j values - initial word vectors and biases. This is useful for fine-tuning. For example one can pretrain model on large corpus (such as wikipedia dump) and then fine tune on smaller task-specific dataset

See Also

http://nlp.stanford.edu/projects/glove/

Examples

# NOT RUN {
temp = tempfile()
download.file('http://mattmahoney.net/dc/text8.zip', temp)
text8 = readLines(unz(temp, "text8"))
it = itoken(text8)
vocabulary = create_vocabulary(it) %>%
  prune_vocabulary(term_count_min = 5)
v_vect = vocab_vectorizer(vocabulary)
tcm = create_tcm(it, v_vect, skip_grams_window = 5L)
glove_model = GloVe$new(word_vectors_size = 50,
  vocabulary = vocabulary, x_max = 10, learning_rate = .25)
# fit model and get word vectors
word_vectors_main = glove_model$fit_transform(tcm, n_iter = 10)
word_vectors_context = glove_model$components
word_vectors = word_vectors_main + t(word_vectors_context)
# }