<?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 for Information Flow</title>
	<atom:link href="http://blogs.acrolinx.com/andrew/comments/feed/" rel="self" type="application/rss+xml" />
	<link>http://blogs.acrolinx.com/andrew</link>
	<description>Musings on Enterprise Information</description>
	<lastBuildDate>Sat, 28 Aug 2010 22:52:23 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>Comment on End-to-End Solutions? Where are the Ends? by Tweets that mention Information Flow » Blog Archive » End-to-End Solutions? Where are the Ends? -- Topsy.com</title>
		<link>http://blogs.acrolinx.com/andrew/2010/08/27/end-to-end-solutions-where-are-the-ends/comment-page-1/#comment-403</link>
		<dc:creator>Tweets that mention Information Flow » Blog Archive » End-to-End Solutions? Where are the Ends? -- Topsy.com</dc:creator>
		<pubDate>Sat, 28 Aug 2010 22:52:23 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.acrolinx.com/andrew/?p=44#comment-403</guid>
		<description>[...] This post was mentioned on Twitter by Val Swisher, Andrew Bredenkamp. Andrew Bredenkamp said: End-to-End Solutions? Where are the Ends? ... http://bit.ly/b6F5Px [...]</description>
		<content:encoded><![CDATA[<p>[...] This post was mentioned on Twitter by Val Swisher, Andrew Bredenkamp. Andrew Bredenkamp said: End-to-End Solutions? Where are the Ends? &#8230; <a href="http://bit.ly/b6F5Px" rel="nofollow">http://bit.ly/b6F5Px</a> [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Why your IQ is important for (machine) translation by Übersetzung Englisch Deutsch</title>
		<link>http://blogs.acrolinx.com/andrew/2010/05/14/why-is-your-iq-is-important-for-machine-translation/comment-page-1/#comment-193</link>
		<dc:creator>Übersetzung Englisch Deutsch</dc:creator>
		<pubDate>Sat, 19 Jun 2010 12:33:08 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.acrolinx.com/andrew/?p=26#comment-193</guid>
		<description>It can be difficult to be sure, especially if you aren&#039;t a native or haven&#039;t spent large amounts of time there. That is why language translation services are crucial to this process.</description>
		<content:encoded><![CDATA[<p>It can be difficult to be sure, especially if you aren&#8217;t a native or haven&#8217;t spent large amounts of time there. That is why language translation services are crucial to this process.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Why your IQ is important for (machine) translation by Übersetzung Englisch Deutsch</title>
		<link>http://blogs.acrolinx.com/andrew/2010/05/14/why-is-your-iq-is-important-for-machine-translation/comment-page-1/#comment-192</link>
		<dc:creator>Übersetzung Englisch Deutsch</dc:creator>
		<pubDate>Sat, 19 Jun 2010 10:09:19 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.acrolinx.com/andrew/?p=26#comment-192</guid>
		<description>One of the biggest mistakes that can be made during the marketing process is not being properly familiar with the culture of the country that is desired for expansion. For instance, something seen as cool and even stylish in the home country of the company might actually be perceived as rude or vulgar in another country. It can be difficult to be sure, especially if you aren&#039;t a native or haven&#039;t spent large amounts of time there. That is why language translation services are crucial to this process.</description>
		<content:encoded><![CDATA[<p>One of the biggest mistakes that can be made during the marketing process is not being properly familiar with the culture of the country that is desired for expansion. For instance, something seen as cool and even stylish in the home country of the company might actually be perceived as rude or vulgar in another country. It can be difficult to be sure, especially if you aren&#8217;t a native or haven&#8217;t spent large amounts of time there. That is why language translation services are crucial to this process.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Why your IQ is important for (machine) translation by Tweets that mention Information Flow » Blog Archive » Why your IQ is important for (machine) translation -- Topsy.com</title>
		<link>http://blogs.acrolinx.com/andrew/2010/05/14/why-is-your-iq-is-important-for-machine-translation/comment-page-1/#comment-81</link>
		<dc:creator>Tweets that mention Information Flow » Blog Archive » Why your IQ is important for (machine) translation -- Topsy.com</dc:creator>
		<pubDate>Sat, 15 May 2010 14:57:57 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.acrolinx.com/andrew/?p=26#comment-81</guid>
		<description>[...] This post was mentioned on Twitter by Andrew Bredenkamp. Andrew Bredenkamp said: Why is IQ important for MT: http://bit.ly/awXiOg [...]</description>
		<content:encoded><![CDATA[<p>[...] This post was mentioned on Twitter by Andrew Bredenkamp. Andrew Bredenkamp said: Why is IQ important for MT: <a href="http://bit.ly/awXiOg" rel="nofollow">http://bit.ly/awXiOg</a> [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Why your IQ is important for (machine) translation by Manuel</title>
		<link>http://blogs.acrolinx.com/andrew/2010/05/14/why-is-your-iq-is-important-for-machine-translation/comment-page-1/#comment-79</link>
		<dc:creator>Manuel</dc:creator>
		<pubDate>Fri, 14 May 2010 23:36:20 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.acrolinx.com/andrew/?p=26#comment-79</guid>
		<description>Data alone is not sufficient. GT is a pure statistical approach because F.Och is alergic to anything but statistics. You have done a short test on a general engine that has been designed for general understanding (Mission: &quot;To organize the information of the word&quot;). SMT is the core of an automated translation system, but a lot ofthe quality depends on the systems built around it, modules, pre- and post-processing. Controlling the input actually has little impact on the outcome, unless you are developing very customized systems and thus want the system to &quot;think&quot; and &quot;expect&quot;. It helps, but it is not a goal in itself. The system should be mature enough to deal with some uncontrolled or unexpected areas and still perform.

I see from your tests that GT gists well and it is free :)</description>
		<content:encoded><![CDATA[<p>Data alone is not sufficient. GT is a pure statistical approach because F.Och is alergic to anything but statistics. You have done a short test on a general engine that has been designed for general understanding (Mission: &#8220;To organize the information of the word&#8221;). SMT is the core of an automated translation system, but a lot ofthe quality depends on the systems built around it, modules, pre- and post-processing. Controlling the input actually has little impact on the outcome, unless you are developing very customized systems and thus want the system to &#8220;think&#8221; and &#8220;expect&#8221;. It helps, but it is not a goal in itself. The system should be mature enough to deal with some uncontrolled or unexpected areas and still perform.</p>
<p>I see from your tests that GT gists well and it is free <img src='http://blogs.acrolinx.com/andrew/wp-includes/images/smilies/icon_smile.gif' alt=':)' class='wp-smiley' /> </p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Why your IQ is important for (machine) translation by Mike Unwalla</title>
		<link>http://blogs.acrolinx.com/andrew/2010/05/14/why-is-your-iq-is-important-for-machine-translation/comment-page-1/#comment-78</link>
		<dc:creator>Mike Unwalla</dc:creator>
		<pubDate>Fri, 14 May 2010 15:39:00 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.acrolinx.com/andrew/?p=26#comment-78</guid>
		<description>@Andrew Bredenkamp: For the last 10 years or so, researchers have been telling us that SMT represented a revolution in machine translation; that there would be no more linguistics, no more rules, just data. “Give me enough data,” went their motto, “and we can work miracles!’. Well Google has enough data, but they still have their limitations.

Data alone is not sufficient. You need metadata about the context.</description>
		<content:encoded><![CDATA[<p>@Andrew Bredenkamp: For the last 10 years or so, researchers have been telling us that SMT represented a revolution in machine translation; that there would be no more linguistics, no more rules, just data. “Give me enough data,” went their motto, “and we can work miracles!’. Well Google has enough data, but they still have their limitations.</p>
<p>Data alone is not sufficient. You need metadata about the context.</p>
]]></content:encoded>
	</item>
	<item>
		<title>Comment on Information Development &#8211; the Japanese Way by Manuel Herranz</title>
		<link>http://blogs.acrolinx.com/andrew/2010/03/09/information-development-the-japanese-way/comment-page-1/#comment-7</link>
		<dc:creator>Manuel Herranz</dc:creator>
		<pubDate>Wed, 10 Mar 2010 12:10:53 +0000</pubDate>
		<guid isPermaLink="false">http://blogs.acrolinx.com/andrew/?p=20#comment-7</guid>
		<description>Some good points for all of us who admire &quot;the Japanese way&quot; Andrew. They should be taught in school at an early age. Manuel</description>
		<content:encoded><![CDATA[<p>Some good points for all of us who admire &#8220;the Japanese way&#8221; Andrew. They should be taught in school at an early age. Manuel</p>
]]></content:encoded>
	</item>
</channel>
</rss>
