as_embed

as_wordvec

[.embed

pattern

<code>PsychWordVec</code> uses two types of word vectors data:
<code>wordvec</code> (data.table, with two variables <code>word</code> and <code>vec</code>)
and <code>embed</code> (matrix, with dimensions as columns and words as row names).
Note that matrix operation makes <code>embed</code> much faster than <code>wordvec</code>.
Users are suggested to reshape data to <code>embed</code> before using the other functions.

An integrative toolbox of word embedding research that provides:
(1) a collection of 'pre-trained' static word vectors in the '.RData'
compressed format <https://psychbruce.github.io/WordVector_RData.pdf>;
(2) a group of functions to process, analyze, and visualize word vectors;
(3) a range of tests to examine conceptual associations, including
the Word Embedding Association Test <doi:10.1126/science.aal4230>
and the Relative Norm Distance <doi:10.1073/pnas.1720347115>,
with permutation test of significance; and
(4) a set of training methods to locally train (static) word vectors
from text corpora, including 'Word2Vec' <doi:10.48550/arXiv.1301.3781>,
'GloVe' <doi:10.3115/v1/D14-1162>, and 'FastText' <doi:10.48550/arXiv.1607.04606>.

Han-Wu-Shuang Bao

PsychWordVec

Word Embedding Research Framework for Psychological Science

as_embed function

<dl><dt>x</dt>
<dd>Object to be reshaped. See examples.</dd>
<dt>normalize</dt>
<dd>Normalize all word vectors to unit length?
Defaults to <code>FALSE</code>. See <code>normalize</code>.</dd>
<dt>i, j</dt>
<dd>Row (<code>i</code>) and column (<code>j</code>) filter to be used in <code>embed[i, j]</code>.</dd>
<dt>pattern</dt>
<dd>Regular expression to be used in <code>embed[pattern("...")]</code>.</dd></dl>

Arguments

<ul>
<li><code>as_embed()</code>: From <code>wordvec</code> (data.table) to <code>embed</code> (matrix).</li>
<li><code>as_wordvec()</code>: From <code>embed</code> (matrix) to <code>wordvec</code> (data.table).</li>
</ul>

Functions

Download pre-trained word vectors data (<code>.RData</code>):
<a href="https://psychbruce.github.io/WordVector_RData.pdf">https://psychbruce.github.io/WordVector_RData.pdf</a>

Download

Word vectors data class: wordvec and embed. — as_embed

<dl>

<dt>x</dt>
<dd>Object to be reshaped. See examples.</dd>


<dt>normalize</dt>
<dd>Normalize all word vectors to unit length?
Defaults to <code>FALSE</code>. See <code>normalize</code>.</dd>


<dt>i, j</dt>
<dd>Row (<code>i</code>) and column (<code>j</code>) filter to be used in <code>embed[i, j]</code>.</dd>


<dt>pattern</dt>
<dd>Regular expression to be used in <code>embed[pattern("...")]</code>.</dd>

</dl>

Download pre-trained word vectors data (<code>.RData</code>):
<a href='https://psychbruce.github.io/WordVector_RData.pdf'>https://psychbruce.github.io/WordVector_RData.pdf</a>

as_embed: Word vectors data class: `wordvec` and `embed`.

Description

Usage

Value

Arguments

Functions

Download

See Also

Examples