<?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: The Long Tail&#8217;s Impact on Search Relevance</title>
	<atom:link href="http://www.altsearchengines.com/2007/12/20/the-long-tails-impact-on-search-relevance/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.altsearchengines.com/2007/12/20/the-long-tails-impact-on-search-relevance/</link>
	<description>The most wonderful search engines you've never seen!</description>
	<pubDate>Wed, 03 Dec 2008 23:57:28 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.6.5</generator>
		<item>
		<title>By: 长尾对于搜索准确性的冲击 &#124; Some Yuguo</title>
		<link>http://www.altsearchengines.com/2007/12/20/the-long-tails-impact-on-search-relevance/#comment-30637</link>
		<dc:creator>长尾对于搜索准确性的冲击 &#124; Some Yuguo</dc:creator>
		<pubDate>Sun, 23 Dec 2007 08:08:27 +0000</pubDate>
		<guid isPermaLink="false">http://altsearchengines.com/2007/12/20/the-long-tails-impact-on-search-relevance/#comment-30637</guid>
		<description>[...] 原文:The Long Tail’s Impact on Search Relevance [...]</description>
		<content:encoded><![CDATA[<p>[...] 原文:The Long Tail’s Impact on Search Relevance [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Melek Pulatkonak</title>
		<link>http://www.altsearchengines.com/2007/12/20/the-long-tails-impact-on-search-relevance/#comment-29964</link>
		<dc:creator>Melek Pulatkonak</dc:creator>
		<pubDate>Fri, 21 Dec 2007 02:38:03 +0000</pubDate>
		<guid isPermaLink="false">http://altsearchengines.com/2007/12/20/the-long-tails-impact-on-search-relevance/#comment-29964</guid>
		<description>Hi Nitin, 

Thank you for the comment &#38; question. 

Semantic search can help solve the problem by understanding the query and Web text. We will not be able to replicate the human mind but understanding natural language will be a first step in that direction.

hakia's goal is bring more relevant results both in the head and the long tail. As we progress further in the development, the performance difference will be more visible. Keep on checking us at hakia.com</description>
		<content:encoded><![CDATA[<p>Hi Nitin, </p>
<p>Thank you for the comment &amp; question. </p>
<p>Semantic search can help solve the problem by understanding the query and Web text. We will not be able to replicate the human mind but understanding natural language will be a first step in that direction.</p>
<p>hakia&#8217;s goal is bring more relevant results both in the head and the long tail. As we progress further in the development, the performance difference will be more visible. Keep on checking us at hakia.com</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: NitinK</title>
		<link>http://www.altsearchengines.com/2007/12/20/the-long-tails-impact-on-search-relevance/#comment-29898</link>
		<dc:creator>NitinK</dc:creator>
		<pubDate>Thu, 20 Dec 2007 20:53:00 +0000</pubDate>
		<guid isPermaLink="false">http://altsearchengines.com/2007/12/20/the-long-tails-impact-on-search-relevance/#comment-29898</guid>
		<description>Melek:

Great post! I agree - major search engines have long trained users to provide tiny scraps of data (keyword-ese!) to find the information they are looking for. However, since the search engines cannot yet read minds, the best they can do for results is revert to the mean, which means that Long Tail results get swamped by the most popular results. 

Having said that, I'm not sure what you are proposing in terms of a solution to this problem. You say: "To improve relevancy, try a new approach that moves away from popularity systems."  Could you be more specific? For example, how would Hakia help to improve results relevance for long-tail queries?</description>
		<content:encoded><![CDATA[<p>Melek:</p>
<p>Great post! I agree - major search engines have long trained users to provide tiny scraps of data (keyword-ese!) to find the information they are looking for. However, since the search engines cannot yet read minds, the best they can do for results is revert to the mean, which means that Long Tail results get swamped by the most popular results. </p>
<p>Having said that, I&#8217;m not sure what you are proposing in terms of a solution to this problem. You say: &#8220;To improve relevancy, try a new approach that moves away from popularity systems.&#8221;  Could you be more specific? For example, how would Hakia help to improve results relevance for long-tail queries?</p>
]]></content:encoded>
	</item>
</channel>
</rss>
