<?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: Contextual ads for video coming soon</title>
	<atom:link href="http://www.lostremote.com/2007/03/01/contextual-ads-for-video-coming-soon/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.lostremote.com/2007/03/01/contextual-ads-for-video-coming-soon/</link>
	<description>Where TV Finds the Future</description>
	<pubDate>Mon, 13 Oct 2008 23:13:48 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.5.1</generator>
		<item>
		<title>By: yellowbot</title>
		<link>http://www.lostremote.com/2007/03/01/contextual-ads-for-video-coming-soon/#comment-205313</link>
		<dc:creator>yellowbot</dc:creator>
		<pubDate>Fri, 02 Mar 2007 20:39:02 +0000</pubDate>
		<guid isPermaLink="false">http://www.lostremote.com/2007/03/01/contextual-ads-for-video-coming-soon/#comment-205313</guid>
		<description>Sounds like a very interesting concept...but to actually implement the speech recognition would be the difficult thing.  I think the metadata would be more relevant...unless people use spamming techniques, misspell words, use the wrong synonms, etc (all of which could be solved programatically).</description>
		<content:encoded><![CDATA[<p>Sounds like a very interesting concept&#8230;but to actually implement the speech recognition would be the difficult thing.  I think the metadata would be more relevant&#8230;unless people use spamming techniques, misspell words, use the wrong synonms, etc (all of which could be solved programatically).</p>
]]></content:encoded>
	</item>
</channel>
</rss>
