check_analogy_accuracy

<code>list</code> of questions. Each element of
<code>questions_list</code> is a <code>integer matrix</code> with four columns. It
represents a set of questions related to a particular category. Each
element of matrix is an index of a row in <code>m_word_vectors</code>. See output
of <a rd-options="" href="/link/prepare_analogy_questions?package=text2vec&version=0.3.0" data-mini-rdoc="text2vec::prepare_analogy_questions">prepare_analogy_questions</a> for details

questions_list

word vectors <code>numeric matrix</code>. Each row should
represent a word.

m_word_vectors

<code>logical</code> whether to print messages during evaluation.

verbose


This function checks how well the GloVe word embeddings do on
  the analogy task. For full examples see <a rd-options="" href="/link/glove?package=text2vec&version=0.3.0" data-mini-rdoc="text2vec::glove">glove</a>.


Very fast and memory-friendly tools for text vectorization and
state-of-the-art word embeddings (GloVe). This package provides a
source-agnostic streaming API, which allows researchers to perform analysis
of collections of documents which are much larger than available RAM. All
core functions are parallelized to benefit from multicore machines.

check_analogy_accuracy: Checks accuracy of word embeddings on the analogy task

Description

Usage

Arguments

See Also