txt_clean_word2vec

Standardise text by<ul>
<li>Conversion of text from UTF-8 to ASCII</li>
<li>Keeping only alphanumeric characters: letters and numbers</li>
<li>Removing multiple spaces</li>
<li>Removing leading/trailing spaces</li>
<li>Performing lowercasing</li>
</ul>

Learn vector representations of words by continuous bag of words and skip-gram implementations of the 'word2vec' algorithm.
The techniques are detailed in the paper "Distributed Representations of Words and Phrases and their Compositionality" by Mikolov et al. (2013), available at <arXiv:1310.4546>.

Jan Wijffels

word2vec

Distributed Representations of Words

Kohei Watanabe

BNOSAC 

Max Fomichev

txt_clean_word2vec function

<dl><dt>x</dt>
<dd>a character vector in UTF-8 encoding</dd>
<dt>ascii</dt>
<dd>logical indicating to use <code>iconv</code> to convert the input from UTF-8 to ASCII. Defaults to TRUE.</dd>
<dt>alpha</dt>
<dd>logical indicating to keep only alphanumeric characters. Defaults to TRUE.</dd>
<dt>tolower</dt>
<dd>logical indicating to lowercase <code>x</code>. Defaults to TRUE.</dd>
<dt>trim</dt>
<dd>logical indicating to trim leading/trailing white space. Defaults to TRUE.</dd></dl>

Arguments

Text cleaning specific for input to word2vec — txt_clean_word2vec

<dl>

<dt>x</dt>
<dd>a character vector in UTF-8 encoding</dd>


<dt>ascii</dt>
<dd>logical indicating to use <code>iconv</code> to convert the input from UTF-8 to ASCII. Defaults to TRUE.</dd>


<dt>alpha</dt>
<dd>logical indicating to keep only alphanumeric characters. Defaults to TRUE.</dd>


<dt>tolower</dt>
<dd>logical indicating to lowercase <code>x</code>. Defaults to TRUE.</dd>


<dt>trim</dt>
<dd>logical indicating to trim leading/trailing white space. Defaults to TRUE.</dd>

</dl>

txt_clean_word2vec: Text cleaning specific for input to word2vec

Description

Usage

Value

Arguments

Examples