plot_ect

This functions plot the words in <code>S_words</code> on a 2D plane according to their association with the average vectors of <code>A_words</code> and <code>B_words</code>. A equality line is also added. Words along the equality line have less bias. Words located on the upper side of the equality line have a stronger association with <code>A_words</code> and vice versa.

Conduct various tests for evaluating implicit biases in word embeddings: Word Embedding Association Test (Caliskan et al., 2017), <doi:10.1126/science.aal4230>, Relative Norm Distance (Garg et al., 2018), <doi:10.1073/pnas.1720347115>, Mean Average Cosine Similarity (Mazini et al., 2019) <arXiv:1904.04047>, SemAxis (An et al., 2018) <arXiv:1806.05521>, Relative Negative Sentiment Bias (Sweeney & Najafian, 2019) <doi:10.18653/v1/P19-1162>, and Embedding Coherence Test (Dev & Phillips, 2019) <arXiv:1901.07656>.

Chung-hong Chan

sweater

Speedy Word Embedding Association Test and Extras Using R

plot_ect function

<dl><dt>x</dt>
<dd>an ect object from the ect function.</dd>
<dt>...</dt>
<dd>additional parameters to the underlying <code><a href="/link/plot()?package=sweater&version=0.1.8" data-mini-rdoc="sweater::plot()">plot()</a></code> function</dd></dl>

Arguments

Plot an ECT result on a two-dimensional plane — plot_ect

<dl>

<dt>x</dt>
<dd>an ect object from the ect function.</dd>


<dt>...</dt>
<dd>additional parameters to the underlying <code><a href='https://rdrr.io/r/graphics/plot.default.html'>plot()</a></code> function</dd>

</dl>

plot_ect: Plot an ECT result on a two-dimensional plane

Description

Usage

Value

Arguments