<?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: Google Translation</title>
	<atom:link href="http://faganm.com/blog/2005/10/10/744/feed/" rel="self" type="application/rss+xml" />
	<link>http://faganm.com/blog/2005/10/10/744/</link>
	<description></description>
	<lastBuildDate>Thu, 28 Jul 2011 11:21:17 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
	<item>
		<title>By: Steven</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-1506</link>
		<dc:creator>Steven</dc:creator>
		<pubDate>Fri, 02 Jun 2006 02:34:39 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-1506</guid>
		<description>	&lt;p&gt;the way the new translators are set up they dont go word for word but rather phrase by phrase to get better accuracy&#8230;.correct?&lt;/p&gt;
	&lt;p&gt;It seems google is flexing its muscles and is in early stages of taking the phrase by phrase over the top with some intense compilation.&lt;/p&gt;
	&lt;p&gt;My guess is the want to be capable of translating entire websites instantly and fluently which would unite the whole world to all the info on the internet and not just whats in your language.
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>the way the new translators are set up they dont go word for word but rather phrase by phrase to get better accuracy&#8230;.correct?</p>
<p>It seems google is flexing its muscles and is in early stages of taking the phrase by phrase over the top with some intense compilation.</p>
<p>My guess is the want to be capable of translating entire websites instantly and fluently which would unite the whole world to all the info on the internet and not just whats in your language.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: justine</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-154</link>
		<dc:creator>justine</dc:creator>
		<pubDate>Mon, 26 Dec 2005 23:29:16 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-154</guid>
		<description>	&lt;p&gt;Link Tip&lt;/p&gt;
	&lt;p&gt;&lt;a href=&#039;http://dict.leo.org/&#039; rel=&#039;nofollow&#039;&gt;http://dict.leo.org/&lt;/a&gt;
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Link Tip</p>
<p><a href='http://dict.leo.org/' rel='nofollow'>http://dict.leo.org/</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: nunzio</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-153</link>
		<dc:creator>nunzio</dc:creator>
		<pubDate>Mon, 26 Dec 2005 23:25:08 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-153</guid>
		<description>	&lt;p&gt;Google Sprachtool â€“ Test 1&lt;/p&gt;
	&lt;p&gt;Testsatz: â€žEs war so schÃ¶n mit dir. Wann werden wir uns wiedersehen?â€œ&lt;/p&gt;
	&lt;p&gt;Die Ãœbersetzung: â€œIt was with you when we will so beautifully see itself again?â€œ&lt;/p&gt;
	&lt;p&gt;Die Gegenprobe: â€žEs war mit Ihnen, wenn wir so schÃ¶n uns wieder sehen?â€œ&lt;/p&gt;
	&lt;p&gt;8 mistakes in one sentence, wow!
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Google Sprachtool â€“ Test 1</p>
<p>Testsatz: â€žEs war so schÃ¶n mit dir. Wann werden wir uns wiedersehen?â€œ</p>
<p>Die Ãœbersetzung: â€œIt was with you when we will so beautifully see itself again?â€œ</p>
<p>Die Gegenprobe: â€žEs war mit Ihnen, wenn wir so schÃ¶n uns wieder sehen?â€œ</p>
<p>8 mistakes in one sentence, wow!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Jaak Henno</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-144</link>
		<dc:creator>Jaak Henno</dc:creator>
		<pubDate>Mon, 12 Dec 2005 21:02:23 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-144</guid>
		<description>	&lt;p&gt;A rather classical test of MT systems is double translation, e.g. english-german-back to english; with Google website this is very easy to implement,  two-way translation is provided for all languages. In the following are results of copy-paste two-way translations from a sentence from the same page &lt;a href=&#039;http://www.google.com/language_tools&#039; rel=&#039;nofollow&#039;&gt;http://www.google.com/language_tools&lt;/a&gt; (only European languages were used) - can you tell what was the original sentence?&lt;/p&gt;
	&lt;p&gt;english-language1-english:&lt;br /&gt;
Adjust the homepage Google, the announcements and the keys to announcement in your preselected language over our preference side.&lt;/p&gt;
	&lt;p&gt;english-language2-english:&lt;br /&gt;
Rules the homepage of Google, the messages and the keys to exposure in your language selected via our page of preferences. &lt;/p&gt;
	&lt;p&gt;english-language3-english:&lt;br /&gt;
Fix the homepage of Google, the messages, and the bellboys to the exhibition in its language selected via our page of the preferences. &lt;/p&gt;
	&lt;p&gt;So - &#8220;Adjust the homepage Google, the messages  and the bellboys to the exhibition in its language selected via our page of preferences&#8221;. Clear?
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>A rather classical test of MT systems is double translation, e.g. english-german-back to english; with Google website this is very easy to implement,  two-way translation is provided for all languages. In the following are results of copy-paste two-way translations from a sentence from the same page <a href='http://www.google.com/language_tools' rel='nofollow'>http://www.google.com/language_tools</a> (only European languages were used) &#8211; can you tell what was the original sentence?</p>
<p>english-language1-english:<br />
Adjust the homepage Google, the announcements and the keys to announcement in your preselected language over our preference side.</p>
<p>english-language2-english:<br />
Rules the homepage of Google, the messages and the keys to exposure in your language selected via our page of preferences. </p>
<p>english-language3-english:<br />
Fix the homepage of Google, the messages, and the bellboys to the exhibition in its language selected via our page of the preferences. </p>
<p>So &#8211; &#8220;Adjust the homepage Google, the messages  and the bellboys to the exhibition in its language selected via our page of preferences&#8221;. Clear?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: mfagan</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-92</link>
		<dc:creator>mfagan</dc:creator>
		<pubDate>Thu, 24 Nov 2005 21:27:54 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-92</guid>
		<description>	&lt;p&gt;Interesting. The whole idea of using anything other than humans to compare the quality of translations seems flawed to me..
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Interesting. The whole idea of using anything other than humans to compare the quality of translations seems flawed to me..</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: wolfgang</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-91</link>
		<dc:creator>wolfgang</dc:creator>
		<pubDate>Thu, 24 Nov 2005 21:22:56 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-91</guid>
		<description>	&lt;p&gt;Google hired one of the most famous MT experts, Franz-Josef Och (he was at RWTH Aachen before). They are working on statistical machine translation SMT. One of Google&#8217;s strong point in it is that they have massive computer power. For SMT to work, you need a lot of parallel text (source and translation) to train the engine. Note that the NIST score probably favours SMT in comparison to rule based systems like Systran (RBMT).
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Google hired one of the most famous MT experts, Franz-Josef Och (he was at RWTH Aachen before). They are working on statistical machine translation SMT. One of Google&#8217;s strong point in it is that they have massive computer power. For SMT to work, you need a lot of parallel text (source and translation) to train the engine. Note that the NIST score probably favours SMT in comparison to rule based systems like Systran (RBMT).</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: mara</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-82</link>
		<dc:creator>mara</dc:creator>
		<pubDate>Sat, 12 Nov 2005 20:15:44 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-82</guid>
		<description>	&lt;p&gt;fiecare om are dreptul la viata&lt;br /&gt;
toti oamenii sunt egali in drepturi&lt;br /&gt;
libertatea este atunci cand poti face orice lucru care nu ii deranjezi pe ceilalti
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>fiecare om are dreptul la viata<br />
toti oamenii sunt egali in drepturi<br />
libertatea este atunci cand poti face orice lucru care nu ii deranjezi pe ceilalti</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: mfagan</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-70</link>
		<dc:creator>mfagan</dc:creator>
		<pubDate>Mon, 17 Oct 2005 05:34:02 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-70</guid>
		<description>	&lt;p&gt;I figure google is/has moved all language translation to their own software, but of course I could be wrong&lt;/p&gt;
	&lt;p&gt;thanks for the info though
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>I figure google is/has moved all language translation to their own software, but of course I could be wrong</p>
<p>thanks for the info though</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Fred</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-69</link>
		<dc:creator>Fred</dc:creator>
		<pubDate>Mon, 17 Oct 2005 04:58:37 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-69</guid>
		<description>	&lt;p&gt;It looks like the Google Version of Japanese-English Translation is fooled by variety of Japanese Text that works fine with&lt;/p&gt;
	&lt;p&gt;Excel.co.jp (Fujitsu Ltd OEM)&lt;br /&gt;
Yahoo.co.jp/honyahku (systran)&lt;/p&gt;
	&lt;p&gt;Any clue what is going on? Gievn that MT is very different than translation who do you suggest is working with google on this?&lt;/p&gt;
	&lt;p&gt;Is it possible that they have Japanese Subconractor (maybe someone like Fujitsu that has a 20% leading share of the Japanese Market) ?
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>It looks like the Google Version of Japanese-English Translation is fooled by variety of Japanese Text that works fine with</p>
<p>Excel.co.jp (Fujitsu Ltd OEM)<br />
Yahoo.co.jp/honyahku (systran)</p>
<p>Any clue what is going on? Gievn that MT is very different than translation who do you suggest is working with google on this?</p>
<p>Is it possible that they have Japanese Subconractor (maybe someone like Fujitsu that has a 20% leading share of the Japanese Market) ?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mattt</title>
		<link>http://faganm.com/blog/2005/10/10/744/#comment-67</link>
		<dc:creator>Mattt</dc:creator>
		<pubDate>Sun, 16 Oct 2005 06:16:52 +0000</pubDate>
		<guid isPermaLink="false">http://www.faganfinder.com/wp/2005/10/10/744/#comment-67</guid>
		<description>	&lt;p&gt;Arabic? That sounds like terrorist talk to me, Mike. Are you against Freedom? Why don&#8217;t you and John Kerry take your communist loving translation software and go find some other country to ruin?
&lt;/p&gt;
</description>
		<content:encoded><![CDATA[<p>Arabic? That sounds like terrorist talk to me, Mike. Are you against Freedom? Why don&#8217;t you and John Kerry take your communist loving translation software and go find some other country to ruin?</p>
]]></content:encoded>
	</item>
</channel>
</rss>

