<?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:georss="http://www.georss.org/georss" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:media="http://search.yahoo.com/mrss/"
		>
<channel>
	<title>Comments on: Scott Prevost explains Powerset&#8217;s approach to semantic search</title>
	<atom:link href="http://blog.jonudell.net/2008/09/26/scott-prevost-explains-powersets-approach-to-semantic-search/feed/" rel="self" type="application/rss+xml" />
	<link>http://blog.jonudell.net/2008/09/26/scott-prevost-explains-powersets-approach-to-semantic-search/</link>
	<description>Strategies for Internet citizens</description>
	<lastBuildDate>Mon, 13 Feb 2012 06:40:07 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
	<item>
		<title>By: Powerset&#8217;s Approach to Search : Beyond Search</title>
		<link>http://blog.jonudell.net/2008/09/26/scott-prevost-explains-powersets-approach-to-semantic-search/#comment-125500</link>
		<dc:creator><![CDATA[Powerset&#8217;s Approach to Search : Beyond Search]]></dc:creator>
		<pubDate>Mon, 06 Oct 2008 05:05:50 +0000</pubDate>
		<guid isPermaLink="false">http://jonudell.wordpress.com/?p=667#comment-125500</guid>
		<description><![CDATA[[...] know more about how Microsoft will leverage the aging Xerox Parc technology, you will want to click here to get an introduction to the Perspectives interview conducted on September 30, 2008, with Scott [...]]]></description>
		<content:encoded><![CDATA[<p>[...] know more about how Microsoft will leverage the aging Xerox Parc technology, you will want to click here to get an introduction to the Perspectives interview conducted on September 30, 2008, with Scott [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Scott Prevost Explains Powerset &#124; The Noisy Channel</title>
		<link>http://blog.jonudell.net/2008/09/26/scott-prevost-explains-powersets-approach-to-semantic-search/#comment-125467</link>
		<dc:creator><![CDATA[Scott Prevost Explains Powerset &#124; The Noisy Channel]]></dc:creator>
		<pubDate>Wed, 01 Oct 2008 02:05:03 +0000</pubDate>
		<guid isPermaLink="false">http://jonudell.wordpress.com/?p=667#comment-125467</guid>
		<description><![CDATA[[...] noticed this Jon Udell interview with Scott Prevost, General Manager and Director of Product for Microsoft-acquired Powerset. [...]]]></description>
		<content:encoded><![CDATA[<p>[...] noticed this Jon Udell interview with Scott Prevost, General Manager and Director of Product for Microsoft-acquired Powerset. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Powerset Demo video &#8212; Video Archive</title>
		<link>http://blog.jonudell.net/2008/09/26/scott-prevost-explains-powersets-approach-to-semantic-search/#comment-125458</link>
		<dc:creator><![CDATA[Powerset Demo video &#8212; Video Archive]]></dc:creator>
		<pubDate>Mon, 29 Sep 2008 19:49:09 +0000</pubDate>
		<guid isPermaLink="false">http://jonudell.wordpress.com/?p=667#comment-125458</guid>
		<description><![CDATA[[...] post by Jon Udell made me try Powerset. I already use Wikipedia search for a lot of my queries, so I&#8217;m adding [...]]]></description>
		<content:encoded><![CDATA[<p>[...] post by Jon Udell made me try Powerset. I already use Wikipedia search for a lot of my queries, so I&#8217;m adding [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jon Udell</title>
		<link>http://blog.jonudell.net/2008/09/26/scott-prevost-explains-powersets-approach-to-semantic-search/#comment-125447</link>
		<dc:creator><![CDATA[Jon Udell]]></dc:creator>
		<pubDate>Sat, 27 Sep 2008 14:24:08 +0000</pubDate>
		<guid isPermaLink="false">http://jonudell.wordpress.com/?p=667#comment-125447</guid>
		<description><![CDATA[That&#039;s an interesting example. In general, to compare directly, you&#039;ll want to restrict Google using site:wikipedia.org, so:

site:wikipedia.org jim smith football

Although in this case, it doesn&#039;t matter because the unrestricted results are the same: wikipedia pages for the American and English players are 1 and 2.

In Powerset, they&#039;re 1 and 3. 

Neither, of course, explicitly disambiguates the two players.

There&#039;s a subtler disambiguation to be made as well. Both players&#039; pages include &#039;Birmingham&#039; but that&#039;s also ambiguous, one&#039;s Alabama and the other England.

Here&#039;s how I see it. Making linguistic sense of texts is a long-term challenge. Years ago I interviewed on of the early MT researchers, who said: &quot;It&#039;s more perspiration than inspiration&quot;. 

The trick will be to make as much appropriate and effective use of   this gradually evolving technology as is possible, while avoiding inappropriate/ineffective use to the extent possible. And that&#039;s going to be a real balancing act, which is part of what makes the whole thing so interesting.]]></description>
		<content:encoded><![CDATA[<p>That&#8217;s an interesting example. In general, to compare directly, you&#8217;ll want to restrict Google using site:wikipedia.org, so:</p>
<p>site:wikipedia.org jim smith football</p>
<p>Although in this case, it doesn&#8217;t matter because the unrestricted results are the same: wikipedia pages for the American and English players are 1 and 2.</p>
<p>In Powerset, they&#8217;re 1 and 3. </p>
<p>Neither, of course, explicitly disambiguates the two players.</p>
<p>There&#8217;s a subtler disambiguation to be made as well. Both players&#8217; pages include &#8216;Birmingham&#8217; but that&#8217;s also ambiguous, one&#8217;s Alabama and the other England.</p>
<p>Here&#8217;s how I see it. Making linguistic sense of texts is a long-term challenge. Years ago I interviewed on of the early MT researchers, who said: &#8220;It&#8217;s more perspiration than inspiration&#8221;. </p>
<p>The trick will be to make as much appropriate and effective use of   this gradually evolving technology as is possible, while avoiding inappropriate/ineffective use to the extent possible. And that&#8217;s going to be a real balancing act, which is part of what makes the whole thing so interesting.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ben</title>
		<link>http://blog.jonudell.net/2008/09/26/scott-prevost-explains-powersets-approach-to-semantic-search/#comment-125446</link>
		<dc:creator><![CDATA[Ben]]></dc:creator>
		<pubDate>Sat, 27 Sep 2008 13:05:30 +0000</pubDate>
		<guid isPermaLink="false">http://jonudell.wordpress.com/?p=667#comment-125446</guid>
		<description><![CDATA[It&#039;s really not clear that this approach offers much advantage. Try searching jim smith football in Powerset/Live and Google. The Google result does a reasonable job of finding and presenting the Jim Smith from UK football and the Jim Smith from US football. The Powerset/Live version is a bit of a mix-up. I&#039;m concerned about the risks of clever search producing mashed-up but misleading results as in http://nelh.blogspot.com/2008/09/does-anyone-actually-want-semantic.html]]></description>
		<content:encoded><![CDATA[<p>It&#8217;s really not clear that this approach offers much advantage. Try searching jim smith football in Powerset/Live and Google. The Google result does a reasonable job of finding and presenting the Jim Smith from UK football and the Jim Smith from US football. The Powerset/Live version is a bit of a mix-up. I&#8217;m concerned about the risks of clever search producing mashed-up but misleading results as in <a href="http://nelh.blogspot.com/2008/09/does-anyone-actually-want-semantic.html" rel="nofollow">http://nelh.blogspot.com/2008/09/does-anyone-actually-want-semantic.html</a></p>
]]></content:encoded>
	</item>
</channel>
</rss>

