<?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: Further on the trend following thing</title>
	<atom:link href="http://aleatory.clientsideweb.net/2008/07/09/further-on-the-trend-following-thing/feed/" rel="self" type="application/rss+xml" />
	<link>http://aleatory.clientsideweb.net/2008/07/09/further-on-the-trend-following-thing/</link>
	<description></description>
	<lastBuildDate>Fri, 30 Dec 2011 15:11:29 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
	<item>
		<title>By: Gareth</title>
		<link>http://aleatory.clientsideweb.net/2008/07/09/further-on-the-trend-following-thing/comment-page-1/#comment-24</link>
		<dc:creator>Gareth</dc:creator>
		<pubDate>Thu, 10 Jul 2008 12:14:45 +0000</pubDate>
		<guid isPermaLink="false">http://aleatory.clientsideweb.net/?p=22#comment-24</guid>
		<description>Agreed, Silobreaker looks really cool and I wish they had some kind of API so that the value they create could be reused somehow; another interesting company in the same space is Powerset who create a semantically derived index on top of Wikipedia and can answer questions like “who is brad pit married to”, this one is less interesting to me since I’m looking at commercial/sales focused applications currently rather than mass market advertising driven things. Another small company I came across was Artesian, they claim to have a stack that allows businesses and users to create their own semantically derived indexes on top of selected content, this seems to address the main issues I have with the other two solutions, i.e. that the indexes know nothing about “you”, this is a really interesting area IMO which I need to investigate more; it seems unclear to me which is the best way to go for business applications</description>
		<content:encoded><![CDATA[<p>Agreed, Silobreaker looks really cool and I wish they had some kind of API so that the value they create could be reused somehow; another interesting company in the same space is Powerset who create a semantically derived index on top of Wikipedia and can answer questions like “who is brad pit married to”, this one is less interesting to me since I’m looking at commercial/sales focused applications currently rather than mass market advertising driven things. Another small company I came across was Artesian, they claim to have a stack that allows businesses and users to create their own semantically derived indexes on top of selected content, this seems to address the main issues I have with the other two solutions, i.e. that the indexes know nothing about “you”, this is a really interesting area IMO which I need to investigate more; it seems unclear to me which is the best way to go for business applications</p>
]]></content:encoded>
	</item>
</channel>
</rss>

