<?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: Testing Google&#8217;s Language Detection</title>
	<atom:link href="http://mitcho.com/blog/observation/testing-googles-language-detection/feed/" rel="self" type="application/rss+xml" />
	<link>http://mitcho.com/blog/observation/testing-googles-language-detection/</link>
	<description></description>
	<lastBuildDate>Fri, 12 Mar 2010 14:57:24 -0500</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: hangfromthefloor (みいし)</title>
		<link>http://mitcho.com/blog/observation/testing-googles-language-detection/comment-page-1/#comment-313</link>
		<dc:creator>hangfromthefloor (みいし)</dc:creator>
		<pubDate>Mon, 26 May 2008 19:01:01 +0000</pubDate>
		<guid isPermaLink="false">http://mitcho.com/blog/?p=254#comment-313</guid>
		<description>&lt;p&gt;Well written; I noticed the same thing recently when I searched for the Japanese variant and the majority of search results came up in Chinese.&lt;/p&gt;

&lt;p&gt;I don&#039;t know if you&#039;ve noticed, but the new Google Translate interface has since recently allowed detection of the input language; however, it is similarly buggy: sometimes when providing Croatian text (for which translation support is included), the application identifies the language as Serbian or Bosnian (for which support is not included). It amuses me that Google detects languages quite decently (albeit with a longer text sample) even for languages it does not support.&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Well written; I noticed the same thing recently when I searched for the Japanese variant and the majority of search results came up in Chinese.</p>

<p>I don&#8217;t know if you&#8217;ve noticed, but the new Google Translate interface has since recently allowed detection of the input language; however, it is similarly buggy: sometimes when providing Croatian text (for which translation support is included), the application identifies the language as Serbian or Bosnian (for which support is not included). It amuses me that Google detects languages quite decently (albeit with a longer text sample) even for languages it does not support.</p>]]></content:encoded>
	</item>
</channel>
</rss>
