sum_wordvec

Calculate the sum vector of multiple words.

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

sum_wordvec function

<dl><dt>data</dt>
<dd>A <code>wordvec</code> (data.table) or <code>embed</code> (matrix), see <code>data_wordvec_load()</code>.</dd>
<dt>x</dt>
<dd>Can be:<ul>
<li><code>NULL</code>: use the sum of all word vectors in <code>data</code></li>
<li>a single word:<ul>
<li><code>"China"</code></li>
</ul></li>
<li>a vector of words:<ul>
<li><code>c("king", "queen")</code></li>
<li><code>cc(" king , queen ; man | woman")</code></li>
</ul></li>
<li>an R formula (<code>~ xxx</code>) specifying words that positively and negatively contribute to the similarity (for word analogy):<ul>
<li><code>~ boy - he + she</code></li>
<li><code>~ king - man + woman</code></li>
<li><code>~ Beijing - China + Japan</code></li>
</ul></li>
</ul></dd>
<dt>verbose</dt>
<dd>Print information to the console? Defaults to <code>TRUE</code>.</dd></dl>

Arguments

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

Calculate the sum vector of multiple words. — sum_wordvec

<dl>

<dt>data</dt>
<dd>A <code>wordvec</code> (data.table) or <code>embed</code> (matrix), see <code>data_wordvec_load()</code>.</dd>


<dt>x</dt>
<dd>Can be:<ul>
<li><code>NULL</code>: use the sum of all word vectors in <code>data</code></li>
<li>a single word:<ul>
<li><code>"China"</code></li>
</ul></li>
<li>a vector of words:<ul>
<li><code>c("king", "queen")</code></li>
<li><code>cc(" king , queen ; man | woman")</code></li>
</ul></li>
<li>an R formula (<code>~ xxx</code>) specifying words that positively and negatively contribute to the similarity (for word analogy):<ul>
<li><code>~ boy - he + she</code></li>
<li><code>~ king - man + woman</code></li>
<li><code>~ Beijing - China + Japan</code></li>
</ul></li>
</ul></dd>


<dt>verbose</dt>
<dd>Print information to the console? Defaults to <code>TRUE</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>

sum_wordvec: Calculate the sum vector of multiple words.

Description

Usage

Value

Arguments

Download

See Also

Examples