<?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/"
	xmlns:media="http://search.yahoo.com/mrss/"
		>
<channel>
	<title>Comments on: Proximity is a hack</title>
	<atom:link href="http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/feed/" rel="self" type="application/rss+xml" />
	<link>http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/</link>
	<description>Tidbits</description>
	<lastBuildDate>Tue, 06 Jan 2009 22:23:28 +0000</lastBuildDate>
	<generator>http://wordpress.com/</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Interesting, Cool &#38; Useful - Sep 12 - Dave Naffziger&#8217;s Blog</title>
		<link>http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-927</link>
		<dc:creator>Interesting, Cool &#38; Useful - Sep 12 - Dave Naffziger&#8217;s Blog</dc:creator>
		<pubDate>Wed, 12 Sep 2007 07:00:53 +0000</pubDate>
		<guid isPermaLink="false">http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-927</guid>
		<description>[...] Proximity is a Hack. Tim Converse, formerly of Yahoo Search and now at Powerset, offers a great writeup about the limits of keyword proximity in determining relevance. [...]</description>
		<content:encoded><![CDATA[<p>[...] Proximity is a Hack. Tim Converse, formerly of Yahoo Search and now at Powerset, offers a great writeup about the limits of keyword proximity in determining relevance. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Negative SEO blog : SEOassassin &#187; &#8220;Natural language processing&#8221; my natural black ass&#8230;</title>
		<link>http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-500</link>
		<dc:creator>Negative SEO blog : SEOassassin &#187; &#8220;Natural language processing&#8221; my natural black ass&#8230;</dc:creator>
		<pubDate>Tue, 31 Jul 2007 12:07:26 +0000</pubDate>
		<guid isPermaLink="false">http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-500</guid>
		<description>[...] Tim has a thought-provoking post about proximity and it&#8217;s uses and limitations, &#8220;Proximity is a hack&#8220;. I&#8217;ll let you read it youself, as it is quite long, but it&#8217;s well worth [...]</description>
		<content:encoded><![CDATA[<p>[...] Tim has a thought-provoking post about proximity and it&#8217;s uses and limitations, &#8220;Proximity is a hack&#8220;. I&#8217;ll let you read it youself, as it is quite long, but it&#8217;s well worth [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Tim Wintle</title>
		<link>http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-482</link>
		<dc:creator>Tim Wintle</dc:creator>
		<pubDate>Mon, 16 Jul 2007 15:21:54 +0000</pubDate>
		<guid isPermaLink="false">http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-482</guid>
		<description>Have to say this is a theme I have heard coming from multiple sources recently, about moving away from pure vector based semantics.

I certainly do not agree with saying that we have squeezed as much as we can out of vector models, although possibly out of pure linear spaces. 

I definately agree with the idea of doing further linguistic work to the text first, though, and I thoroughly enjoyed this article. I think the emphasis has to go on combining something along the lines of neural networks with the existing vector models, where many people I have heard talking about this recently have suggested completely removing the vector approach - which seems to be throwing away years of work.</description>
		<content:encoded><![CDATA[<p>Have to say this is a theme I have heard coming from multiple sources recently, about moving away from pure vector based semantics.</p>
<p>I certainly do not agree with saying that we have squeezed as much as we can out of vector models, although possibly out of pure linear spaces. </p>
<p>I definately agree with the idea of doing further linguistic work to the text first, though, and I thoroughly enjoyed this article. I think the emphasis has to go on combining something along the lines of neural networks with the existing vector models, where many people I have heard talking about this recently have suggested completely removing the vector approach &#8211; which seems to be throwing away years of work.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: brendan</title>
		<link>http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-473</link>
		<dc:creator>brendan</dc:creator>
		<pubDate>Fri, 06 Jul 2007 03:56:45 +0000</pubDate>
		<guid isPermaLink="false">http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-473</guid>
		<description>epicycles to epicycles -- I like it!</description>
		<content:encoded><![CDATA[<p>epicycles to epicycles &#8212; I like it!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: randfish</title>
		<link>http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-472</link>
		<dc:creator>randfish</dc:creator>
		<pubDate>Mon, 02 Jul 2007 16:27:30 +0000</pubDate>
		<guid isPermaLink="false">http://timconverse.wordpress.com/2007/06/25/proximity-is-a-hack/#comment-472</guid>
		<description>Tim - so, if I understand you correctly, the idea here is to have the machines actually &quot;understand&quot; context and then use it to make better correlations between term proximity, link relationships, etc, yeah?

Thus, what you&#039;d really have is something close to natural language processing, right?

Gotta say - if Powerset can do it before Google does, there&#039;s going to be a lot of very impressed people out there, myself among them.

BTW - Congrats on the move and the position. Haven&#039;t seen you since Chicago, but hopefully you&#039;ll emerge from coding for San Jose :)</description>
		<content:encoded><![CDATA[<p>Tim &#8211; so, if I understand you correctly, the idea here is to have the machines actually &#8220;understand&#8221; context and then use it to make better correlations between term proximity, link relationships, etc, yeah?</p>
<p>Thus, what you&#8217;d really have is something close to natural language processing, right?</p>
<p>Gotta say &#8211; if Powerset can do it before Google does, there&#8217;s going to be a lot of very impressed people out there, myself among them.</p>
<p>BTW &#8211; Congrats on the move and the position. Haven&#8217;t seen you since Chicago, but hopefully you&#8217;ll emerge from coding for San Jose <img src='http://s.wordpress.com/wp-includes/images/smilies/icon_smile.gif' alt=':)' class='wp-smiley' /> </p>
]]></content:encoded>
	</item>
</channel>
</rss>
