<?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"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: Freebasing</title>
	<atom:link href="http://thenoisychannel.com/2008/10/31/freebasing/feed/" rel="self" type="application/rss+xml" />
	<link>http://thenoisychannel.com/2008/10/31/freebasing/</link>
	<description></description>
	<lastBuildDate>Mon, 21 May 2012 05:21:00 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.2</generator>
	<item>
		<title>By: Freebase Parallax</title>
		<link>http://thenoisychannel.com/2008/10/31/freebasing/comment-page-1/#comment-1015</link>
		<dc:creator>Freebase Parallax</dc:creator>
		<pubDate>Wed, 03 Dec 2008 05:11:29 +0000</pubDate>
		<guid isPermaLink="false">http://thenoisychannel.com/?p=719#comment-1015</guid>
		<description>[...] (via The Noisy Channel) [...]</description>
		<content:encoded><![CDATA[<p>[...] (via The Noisy Channel) [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Daniel Lemire</title>
		<link>http://thenoisychannel.com/2008/10/31/freebasing/comment-page-1/#comment-673</link>
		<dc:creator>Daniel Lemire</dc:creator>
		<pubDate>Fri, 31 Oct 2008 19:04:24 +0000</pubDate>
		<guid isPermaLink="false">http://thenoisychannel.com/?p=719#comment-673</guid>
		<description>I wrote something just like it with a post-doc, except that it uses only tag clouds. I even made a paper out of it:

http://arxiv.org/abs/0710.2156

I bet they share a lot of my intuition, so maybe the intro. of my paper could help you.

Their design however has one fundamental difference: they use &quot;selection queries&quot; (which architects did this) and they do not have much support for fancier aggregates and clustering... which we worked on.</description>
		<content:encoded><![CDATA[<p>I wrote something just like it with a post-doc, except that it uses only tag clouds. I even made a paper out of it:</p>
<p><a href="http://arxiv.org/abs/0710.2156" rel="nofollow">http://arxiv.org/abs/0710.2156</a></p>
<p>I bet they share a lot of my intuition, so maybe the intro. of my paper could help you.</p>
<p>Their design however has one fundamental difference: they use &#8220;selection queries&#8221; (which architects did this) and they do not have much support for fancier aggregates and clustering&#8230; which we worked on.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

