<?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/"
		>
<channel>
	<title>Comments on: TaQuilla 0.3.0 released</title>
	<atom:link href="http://mesquilla.com/2009/12/22/taquilla-0-3-0-released/feed/" rel="self" type="application/rss+xml" />
	<link>http://mesquilla.com/2009/12/22/taquilla-0-3-0-released/?utm_source=rss&#038;utm_medium=rss&#038;utm_campaign=taquilla-0-3-0-released</link>
	<description>Messaging with Mozilla by rkent</description>
	<lastBuildDate>Thu, 17 May 2012 15:59:50 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
	<item>
		<title>By: Sun W. Kim</title>
		<link>http://mesquilla.com/2009/12/22/taquilla-0-3-0-released/comment-page-1/#comment-3182</link>
		<dc:creator>Sun W. Kim</dc:creator>
		<pubDate>Thu, 22 Mar 2012 03:16:00 +0000</pubDate>
		<guid isPermaLink="false">http://mesquilla.com/?p=569#comment-3182</guid>
		<description>Hi, thanks for explaining the strategy for ham training. I think I got it and started using 3 or Alt+3 to tag or untag. I also am starting with one tag only (Personal) and see how it works. I tried five tags last night and it was a real mess. I have so many message rules right now its not even funny. I am hoping with a little training TaQuilla can help me tagged emails to the desired folder.</description>
		<content:encoded><![CDATA[<p>Hi, thanks for explaining the strategy for ham training. I think I got it and started using 3 or Alt+3 to tag or untag. I also am starting with one tag only (Personal) and see how it works. I tried five tags last night and it was a real mess. I have so many message rules right now its not even funny. I am hoping with a little training TaQuilla can help me tagged emails to the desired folder.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: rkent</title>
		<link>http://mesquilla.com/2009/12/22/taquilla-0-3-0-released/comment-page-1/#comment-3181</link>
		<dc:creator>rkent</dc:creator>
		<pubDate>Wed, 21 Mar 2012 22:05:10 +0000</pubDate>
		<guid isPermaLink="false">http://mesquilla.com/?p=569#comment-3181</guid>
		<description>Not only does it make it &quot;smarter&quot;, but it is really essential that you train both good and bad hits.

And that is the biggest issue with TaQuilla. There really is not an adequate UI for the ham training (an issue that core Thunderbird also has for spam as well). Really the only practical way to make it work is to enable keyboard shortcuts, and then make sure that you train both good and bad items. You don&#039;t need to actually train on rrors, you can just pick a number of existing items that hit and don&#039;t hit, and train on those.</description>
		<content:encoded><![CDATA[<p>Not only does it make it &#8220;smarter&#8221;, but it is really essential that you train both good and bad hits.</p>
<p>And that is the biggest issue with TaQuilla. There really is not an adequate UI for the ham training (an issue that core Thunderbird also has for spam as well). Really the only practical way to make it work is to enable keyboard shortcuts, and then make sure that you train both good and bad items. You don&#8217;t need to actually train on rrors, you can just pick a number of existing items that hit and don&#8217;t hit, and train on those.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sun W. Kim</title>
		<link>http://mesquilla.com/2009/12/22/taquilla-0-3-0-released/comment-page-1/#comment-3180</link>
		<dc:creator>Sun W. Kim</dc:creator>
		<pubDate>Wed, 21 Mar 2012 21:28:54 +0000</pubDate>
		<guid isPermaLink="false">http://mesquilla.com/?p=569#comment-3180</guid>
		<description>Thanks, I figured it out last night.

Does removing tags make the Bayesian filter make it learn (make it smarter)? I know with SpamBayes for Outlook, marking a false spam as &quot;Ham&quot; makes it smarter. 

I also am not sure how to handle an e-mail being tagged multiple times. Since I want to move e-mails to a folder based on their tag, having multiple tags throws a wrench into the process.</description>
		<content:encoded><![CDATA[<p>Thanks, I figured it out last night.</p>
<p>Does removing tags make the Bayesian filter make it learn (make it smarter)? I know with SpamBayes for Outlook, marking a false spam as &#8220;Ham&#8221; makes it smarter. </p>
<p>I also am not sure how to handle an e-mail being tagged multiple times. Since I want to move e-mails to a folder based on their tag, having multiple tags throws a wrench into the process.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: rkent</title>
		<link>http://mesquilla.com/2009/12/22/taquilla-0-3-0-released/comment-page-1/#comment-3179</link>
		<dc:creator>rkent</dc:creator>
		<pubDate>Wed, 21 Mar 2012 15:47:34 +0000</pubDate>
		<guid isPermaLink="false">http://mesquilla.com/?p=569#comment-3179</guid>
		<description>TaQuilla&#039;s tags are the same as the email tags that are part of the core Thunderbird application. So they are setup in Tools/Options/Display/Tags, but must be enabled for bayes analysis in Tools/Addons/TaQuilla/Options before they will be analyzed.</description>
		<content:encoded><![CDATA[<p>TaQuilla&#8217;s tags are the same as the email tags that are part of the core Thunderbird application. So they are setup in Tools/Options/Display/Tags, but must be enabled for bayes analysis in Tools/Addons/TaQuilla/Options before they will be analyzed.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sun W. Kim</title>
		<link>http://mesquilla.com/2009/12/22/taquilla-0-3-0-released/comment-page-1/#comment-3178</link>
		<dc:creator>Sun W. Kim</dc:creator>
		<pubDate>Wed, 21 Mar 2012 04:13:27 +0000</pubDate>
		<guid isPermaLink="false">http://mesquilla.com/?p=569#comment-3178</guid>
		<description>I&#039;m curious why we don&#039;t have the option of labelling our tags? If you are tagging &quot;Sports&quot;, I am not sure where you can set this up using TaQuilla. Maybe I am misunderstanding how that is done.</description>
		<content:encoded><![CDATA[<p>I&#8217;m curious why we don&#8217;t have the option of labelling our tags? If you are tagging &#8220;Sports&#8221;, I am not sure where you can set this up using TaQuilla. Maybe I am misunderstanding how that is done.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jakub Kaplan</title>
		<link>http://mesquilla.com/2009/12/22/taquilla-0-3-0-released/comment-page-1/#comment-92</link>
		<dc:creator>Jakub Kaplan</dc:creator>
		<pubDate>Thu, 24 Dec 2009 09:27:45 +0000</pubDate>
		<guid isPermaLink="false">http://mesquilla.com/?p=569#comment-92</guid>
		<description>Thanks a lot, will try it out.

I have been looking forward to it, as separating important e-mails from e-mails that are not important is the usually phase 1 of my Inbox processing, and I think that for a fair portion the decision can be made by a classifier.</description>
		<content:encoded><![CDATA[<p>Thanks a lot, will try it out.</p>
<p>I have been looking forward to it, as separating important e-mails from e-mails that are not important is the usually phase 1 of my Inbox processing, and I think that for a fair portion the decision can be made by a classifier.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

