<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	>
<channel>
	<title>Comments on: The forest for the trees</title>
	<atom:link href="http://www.alexlinsker.com/2007/09/08/how-to-show-a-computer-the-forest-for-the-trees/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.alexlinsker.com/2007/09/08/how-to-show-a-computer-the-forest-for-the-trees/</link>
	<description>Where I throw spaghetti on the wall to see what sticks</description>
	<pubDate>Fri, 21 Nov 2008 02:48:25 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.6</generator>
		<item>
		<title>By: smitty</title>
		<link>http://www.alexlinsker.com/2007/09/08/how-to-show-a-computer-the-forest-for-the-trees/#comment-727</link>
		<dc:creator>smitty</dc:creator>
		<pubDate>Tue, 11 Sep 2007 00:32:07 +0000</pubDate>
		<guid isPermaLink="false">http://www.alexlinsker.com/2007/09/08/how-to-show-a-computer-the-forest-for-the-trees/#comment-727</guid>
		<description>i just wonder how that algorithm would pan out.  for example,  how could it tell if i'm telling a fictional story, pasting in an excerpt from a book, or talking about what happened to me last night at a party?

also, if i am writing an email about my exploits last night, should it show ads for "prose" ?

another way of looking at this, is from the advertising perspective. i'm currently reading a book on marketing, and he talks about examples from different niches.  what about, when he's talking about food marketing, i see ads for food.  maybe i am in a more receptable place for that particular ad, even though the actual topic is "marketing" ?

but that last piece is just a value question.  what you're talking about is
for the search engines to have a higher comprehension of what a set of words is really about.  to understand the meaning, to deduce based on consistent subtleties, without conflicting elsewhere.  it's not easy, and is the holy grail so to speak of that industry...

"should I ask her" could be referring to someone thinking of starting a
relationship, 
but it could also mean "if she's pregnant" or "how old she is" - the goal here is simple:
know all the potential endings for the phrase "should i ask her" and then analyze the surrounding text to see which of those potential endings matches.

they will be there... from what i've seen, the fact that they're not there,
is evidence of how hard this really is...</description>
		<content:encoded><![CDATA[<p>i just wonder how that algorithm would pan out.  for example,  how could it tell if i&#8217;m telling a fictional story, pasting in an excerpt from a book, or talking about what happened to me last night at a party?</p>
<p>also, if i am writing an email about my exploits last night, should it show ads for &#8220;prose&#8221; ?</p>
<p>another way of looking at this, is from the advertising perspective. i&#8217;m currently reading a book on marketing, and he talks about examples from different niches.  what about, when he&#8217;s talking about food marketing, i see ads for food.  maybe i am in a more receptable place for that particular ad, even though the actual topic is &#8220;marketing&#8221; ?</p>
<p>but that last piece is just a value question.  what you&#8217;re talking about is<br />
for the search engines to have a higher comprehension of what a set of words is really about.  to understand the meaning, to deduce based on consistent subtleties, without conflicting elsewhere.  it&#8217;s not easy, and is the holy grail so to speak of that industry&#8230;</p>
<p>&#8220;should I ask her&#8221; could be referring to someone thinking of starting a<br />
relationship,<br />
but it could also mean &#8220;if she&#8217;s pregnant&#8221; or &#8220;how old she is&#8221; - the goal here is simple:<br />
know all the potential endings for the phrase &#8220;should i ask her&#8221; and then analyze the surrounding text to see which of those potential endings matches.</p>
<p>they will be there&#8230; from what i&#8217;ve seen, the fact that they&#8217;re not there,<br />
is evidence of how hard this really is&#8230;</p>
]]></content:encoded>
	</item>
</channel>
</rss>
