<?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 Fine Manual</title>
	<atom:link href="http://lr2.com/archives/2006/06/18/the-fine-manual/feed/" rel="self" type="application/rss+xml" />
	<link>http://lr2.com/archives/2006/06/18/the-fine-manual/</link>
	<description>Just another  weblog</description>
	<pubDate>Wed, 07 Jan 2009 17:48:01 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.6.1</generator>
		<item>
		<title>By: Marc</title>
		<link>http://lr2.com/archives/2006/06/18/the-fine-manual/#comment-3133</link>
		<dc:creator>Marc</dc:creator>
		<pubDate>Sun, 18 Jun 2006 19:27:57 +0000</pubDate>
		<guid isPermaLink="false">http://lr2.com/archives/2006/06/18/the-fine-manual/#comment-3133</guid>
		<description>Rudeness drives people away. On the other hand, asking questions about things that are in the manual is rude to the developers and other users. My response would probably be "I think that's in the manual or the FAQ". Anything more is not only rude but is taking too much of my time.

I think a nice technological solution would be to have some kind of intelligent agent that scans the question and finds things that are in the manual or FAQ and auto responds with the answer. This is hard in the general case but might not  be very hard to do for a small subset of frequently asked questions. I suspect that a Bayesian classifier could probably be trained to do this sort of classification.</description>
		<content:encoded><![CDATA[<p>Rudeness drives people away. On the other hand, asking questions about things that are in the manual is rude to the developers and other users. My response would probably be &#8220;I think that&#8217;s in the manual or the FAQ&#8221;. Anything more is not only rude but is taking too much of my time.</p>
<p>I think a nice technological solution would be to have some kind of intelligent agent that scans the question and finds things that are in the manual or FAQ and auto responds with the answer. This is hard in the general case but might not  be very hard to do for a small subset of frequently asked questions. I suspect that a Bayesian classifier could probably be trained to do this sort of classification.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
