<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Word2Vec Embeddings on CS-301</title>
    <link>http://pantelis.github.io/cs301/docs/common/lectures/nlp/word2vec/</link>
    <description>Recent content in Word2Vec Embeddings on CS-301</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language><atom:link href="http://pantelis.github.io/cs301/docs/common/lectures/nlp/word2vec/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Word2Vec Workshop</title>
      <link>http://pantelis.github.io/cs301/docs/common/lectures/nlp/word2vec/word2vec-workshop/</link>
      <pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate>
      
      <guid>http://pantelis.github.io/cs301/docs/common/lectures/nlp/word2vec/word2vec-workshop/</guid>
      <description>Word2Vec Workshop #  Example #  The following example is from here.  Consider the training corpus having the following sentences:
“the dog saw a cat”,
“the dog chased the cat”,
“the cat climbed a tree”
In this corpus $V=8$ and we are interested in creating word embeddings of order $d=3$. The parameter matrices are randomly initialized as
$$W = \begin{bmatrix} 0.54 &amp;amp; 0.28 &amp;amp; 0.42\\0.84 &amp;amp; 0.00 &amp;amp; 0.</description>
    </item>
    
  </channel>
</rss>
