<article>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#article10_03_09_2116249</id>
	<title>Google's Computing Power Refines Translation</title>
	<author>kdawson</author>
	<datestamp>1268135280000</datestamp>
	<htmltext>gollum123 sends an excerpt from the NY Times on how <a href="http://www.nytimes.com/2010/03/09/technology/09translate.html?hpw&amp;pagewanted=all">Google has taken a lead in language translation</a>, in one of the company's few unqualified successes as it attempts to broaden its offerings beyond search. <i>"...Google's quick rise to the top echelons of the translation business is a reminder of what can happen when Google unleashes its brute-force computing power on complex problems. The network of data centers that it built for Web searches may now be, when lashed together, the world's largest computer. Google is using that machine to push the limits on translation technology. Last month, for example, it said it was working to combine its translation tool with image analysis, allowing a person to, say, take a cellphone photo of a menu in German and get an instant English translation. ...in the mid-1990s, researchers began favoring a so-called statistical approach. They found that if they fed the computer thousands or millions of passages and their human-generated translations, it could learn to make accurate guesses about how to translate new texts. It turns out that this technique, which requires huge amounts of data and lots of computing horsepower, is right up Google's alley. ...Google's service is good enough to convey the essence of a news article, and it has become a quick source for translations for millions of people."</i></htmltext>
<tokenext>gollum123 sends an excerpt from the NY Times on how Google has taken a lead in language translation , in one of the company 's few unqualified successes as it attempts to broaden its offerings beyond search .
" ...Google 's quick rise to the top echelons of the translation business is a reminder of what can happen when Google unleashes its brute-force computing power on complex problems .
The network of data centers that it built for Web searches may now be , when lashed together , the world 's largest computer .
Google is using that machine to push the limits on translation technology .
Last month , for example , it said it was working to combine its translation tool with image analysis , allowing a person to , say , take a cellphone photo of a menu in German and get an instant English translation .
...in the mid-1990s , researchers began favoring a so-called statistical approach .
They found that if they fed the computer thousands or millions of passages and their human-generated translations , it could learn to make accurate guesses about how to translate new texts .
It turns out that this technique , which requires huge amounts of data and lots of computing horsepower , is right up Google 's alley .
...Google 's service is good enough to convey the essence of a news article , and it has become a quick source for translations for millions of people .
"</tokentext>
<sentencetext>gollum123 sends an excerpt from the NY Times on how Google has taken a lead in language translation, in one of the company's few unqualified successes as it attempts to broaden its offerings beyond search.
"...Google's quick rise to the top echelons of the translation business is a reminder of what can happen when Google unleashes its brute-force computing power on complex problems.
The network of data centers that it built for Web searches may now be, when lashed together, the world's largest computer.
Google is using that machine to push the limits on translation technology.
Last month, for example, it said it was working to combine its translation tool with image analysis, allowing a person to, say, take a cellphone photo of a menu in German and get an instant English translation.
...in the mid-1990s, researchers began favoring a so-called statistical approach.
They found that if they fed the computer thousands or millions of passages and their human-generated translations, it could learn to make accurate guesses about how to translate new texts.
It turns out that this technique, which requires huge amounts of data and lots of computing horsepower, is right up Google's alley.
...Google's service is good enough to convey the essence of a news article, and it has become a quick source for translations for millions of people.
"</sentencetext>
</article>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424618</id>
	<title>Re:Similar languages</title>
	<author>bunkymag</author>
	<datestamp>1268223660000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext>Jeez.. that was fun, but its Japanese translation ability makes even Babelfish look like an absolute translation genius. Very, very, very, very basic.</htmltext>
<tokenext>Jeez.. that was fun , but its Japanese translation ability makes even Babelfish look like an absolute translation genius .
Very , very , very , very basic .</tokentext>
<sentencetext>Jeez.. that was fun, but its Japanese translation ability makes even Babelfish look like an absolute translation genius.
Very, very, very, very basic.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422472</id>
	<title>Re:Similar languages</title>
	<author>Anonymous</author>
	<datestamp>1268150580000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Pfft. That site doesn't work with Firefox 3.6, only IE.</p></htmltext>
<tokenext>Pfft .
That site does n't work with Firefox 3.6 , only IE .</tokentext>
<sentencetext>Pfft.
That site doesn't work with Firefox 3.6, only IE.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704</id>
	<title>Why is machine translation so difficult?</title>
	<author>Anonymous</author>
	<datestamp>1268143020000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>That's what I've never understood. Why can't software translate as easily as a human? Is it really that difficult to come up with a set of rules so things are worded correctly?</p></htmltext>
<tokenext>That 's what I 've never understood .
Why ca n't software translate as easily as a human ?
Is it really that difficult to come up with a set of rules so things are worded correctly ?</tokentext>
<sentencetext>That's what I've never understood.
Why can't software translate as easily as a human?
Is it really that difficult to come up with a set of rules so things are worded correctly?</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421336</id>
	<title>somebody has to say this</title>
	<author>zlel</author>
	<datestamp>1268140560000</datestamp>
	<modclass>Insightful</modclass>
	<modscore>1</modscore>
	<htmltext>Granted that Art is not a field foreign to computing, translation is an art that is difficult to satisfactorily automate.
It's not about getting the semantics right, or the meaning right, but to translate a piece of work into another cultural context for another person,
is a bit like trying to read somebody's mind.

The turing test for translation would probably be something like automatically translating a new contemporary musical into another language?
IMHO that's more difficult than getting a computer to write its own musical.

I believe there is a niche for automated translation, but even for the niche it's trying to fill, it's not good enough. Not especially in my part of the world where there is not only
a diversity of languages, but also a great diversity in the language families from which these language take their characteristics.</htmltext>
<tokenext>Granted that Art is not a field foreign to computing , translation is an art that is difficult to satisfactorily automate .
It 's not about getting the semantics right , or the meaning right , but to translate a piece of work into another cultural context for another person , is a bit like trying to read somebody 's mind .
The turing test for translation would probably be something like automatically translating a new contemporary musical into another language ?
IMHO that 's more difficult than getting a computer to write its own musical .
I believe there is a niche for automated translation , but even for the niche it 's trying to fill , it 's not good enough .
Not especially in my part of the world where there is not only a diversity of languages , but also a great diversity in the language families from which these language take their characteristics .</tokentext>
<sentencetext>Granted that Art is not a field foreign to computing, translation is an art that is difficult to satisfactorily automate.
It's not about getting the semantics right, or the meaning right, but to translate a piece of work into another cultural context for another person,
is a bit like trying to read somebody's mind.
The turing test for translation would probably be something like automatically translating a new contemporary musical into another language?
IMHO that's more difficult than getting a computer to write its own musical.
I believe there is a niche for automated translation, but even for the niche it's trying to fill, it's not good enough.
Not especially in my part of the world where there is not only
a diversity of languages, but also a great diversity in the language families from which these language take their characteristics.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423390</id>
	<title>Re:For western languages...</title>
	<author>greenguy</author>
	<datestamp>1268160960000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>I'm also in the business, and frankly, I'm not impressed. Google Translator is a stopgap at best. A lot of posts here have said it's good enough for basic phrases, and that may be true, but how far is that going to get you? Great, you can read short phrases... assuming they're not too obscure, and that they're written correctly and legibly in the source language, and that there's not some double entendre going on, and that Google understands both the dialect being translated and <i>your</i> dialect, and so on...</p><p>Basically, good translation requires a vast amount of context -- both within a given document and in the broader culture. Google can accrue billions of documents that are reasonably good translations, but it can't accrue their context. The very fact that it's lumped them all together strips out their context. And what's appropriate in one context is quite inappropriate in another. [Insert well-worn anecdote about the Spanish verb "coger" here.] This simply can't be automated, because the same translator works in a variety of contexts, and will make different decisions at different times.</p><p>An obvious example: most languages have two or more levels of address, depending on social distance. English does not. English doesn't distinguish between the subject and object form, or even the singular and plural, in the word "you," and nearly every other language does. That means there are three independent decisions to make when translating that word, with two or three or four reasonable choices for each. And that doesn't count word order, or colloquial usage that wouldn't translate directly at all. That's all dependent on context.</p><p>In short, professionals won't be in danger any time soon.</p></htmltext>
<tokenext>I 'm also in the business , and frankly , I 'm not impressed .
Google Translator is a stopgap at best .
A lot of posts here have said it 's good enough for basic phrases , and that may be true , but how far is that going to get you ?
Great , you can read short phrases... assuming they 're not too obscure , and that they 're written correctly and legibly in the source language , and that there 's not some double entendre going on , and that Google understands both the dialect being translated and your dialect , and so on...Basically , good translation requires a vast amount of context -- both within a given document and in the broader culture .
Google can accrue billions of documents that are reasonably good translations , but it ca n't accrue their context .
The very fact that it 's lumped them all together strips out their context .
And what 's appropriate in one context is quite inappropriate in another .
[ Insert well-worn anecdote about the Spanish verb " coger " here .
] This simply ca n't be automated , because the same translator works in a variety of contexts , and will make different decisions at different times.An obvious example : most languages have two or more levels of address , depending on social distance .
English does not .
English does n't distinguish between the subject and object form , or even the singular and plural , in the word " you , " and nearly every other language does .
That means there are three independent decisions to make when translating that word , with two or three or four reasonable choices for each .
And that does n't count word order , or colloquial usage that would n't translate directly at all .
That 's all dependent on context.In short , professionals wo n't be in danger any time soon .</tokentext>
<sentencetext>I'm also in the business, and frankly, I'm not impressed.
Google Translator is a stopgap at best.
A lot of posts here have said it's good enough for basic phrases, and that may be true, but how far is that going to get you?
Great, you can read short phrases... assuming they're not too obscure, and that they're written correctly and legibly in the source language, and that there's not some double entendre going on, and that Google understands both the dialect being translated and your dialect, and so on...Basically, good translation requires a vast amount of context -- both within a given document and in the broader culture.
Google can accrue billions of documents that are reasonably good translations, but it can't accrue their context.
The very fact that it's lumped them all together strips out their context.
And what's appropriate in one context is quite inappropriate in another.
[Insert well-worn anecdote about the Spanish verb "coger" here.
] This simply can't be automated, because the same translator works in a variety of contexts, and will make different decisions at different times.An obvious example: most languages have two or more levels of address, depending on social distance.
English does not.
English doesn't distinguish between the subject and object form, or even the singular and plural, in the word "you," and nearly every other language does.
That means there are three independent decisions to make when translating that word, with two or three or four reasonable choices for each.
And that doesn't count word order, or colloquial usage that wouldn't translate directly at all.
That's all dependent on context.In short, professionals won't be in danger any time soon.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421406</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421684</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>Anonymous</author>
	<datestamp>1268142780000</datestamp>
	<modclass>Insightful</modclass>
	<modscore>4</modscore>
	<htmltext>Not to disagree with the results of your test, but I think a better test would be actual translations from authentic Chinese text to English. Going from English to Chinese to English is like taking an English interpretation of what the Chinese are trying to interpret from what someone was saying authentically in English instead of just interpreting into English what someone was authentically saying in Chinese.</htmltext>
<tokenext>Not to disagree with the results of your test , but I think a better test would be actual translations from authentic Chinese text to English .
Going from English to Chinese to English is like taking an English interpretation of what the Chinese are trying to interpret from what someone was saying authentically in English instead of just interpreting into English what someone was authentically saying in Chinese .</tokentext>
<sentencetext>Not to disagree with the results of your test, but I think a better test would be actual translations from authentic Chinese text to English.
Going from English to Chinese to English is like taking an English interpretation of what the Chinese are trying to interpret from what someone was saying authentically in English instead of just interpreting into English what someone was authentically saying in Chinese.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421290</id>
	<title>Pffft...</title>
	<author>Anonymous</author>
	<datestamp>1268140260000</datestamp>
	<modclass>Insightful</modclass>
	<modscore>2</modscore>
	<htmltext>For Chinese, just using a character dictionary is better because the translations in Google are so bad. Unfortunately, I must do this on a daily basis. Google is good at search, but cataloging the entire Web is a much easier job than learning Chinese.</htmltext>
<tokenext>For Chinese , just using a character dictionary is better because the translations in Google are so bad .
Unfortunately , I must do this on a daily basis .
Google is good at search , but cataloging the entire Web is a much easier job than learning Chinese .</tokentext>
<sentencetext>For Chinese, just using a character dictionary is better because the translations in Google are so bad.
Unfortunately, I must do this on a daily basis.
Google is good at search, but cataloging the entire Web is a much easier job than learning Chinese.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31425050</id>
	<title>it's better english, but a better translation ?</title>
	<author>Anonymous</author>
	<datestamp>1268230440000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>of course statistical translations look better, because they optimise<br>exactly that: frequent word sequences in the target language (and related to<br>the input of course).<br>the real question is how well do they match the input meaning.<br>can you tell ?</p></htmltext>
<tokenext>of course statistical translations look better , because they optimiseexactly that : frequent word sequences in the target language ( and related tothe input of course ) .the real question is how well do they match the input meaning.can you tell ?</tokentext>
<sentencetext>of course statistical translations look better, because they optimiseexactly that: frequent word sequences in the target language (and related tothe input of course).the real question is how well do they match the input meaning.can you tell ?</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423514</id>
	<title>Forkbomb</title>
	<author>Anonymous</author>
	<datestamp>1268163300000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>The translator can't seem to figure out exactly how many times the road has diverged...</p><p>"two roads diverged in a yellow wood"<br>http://translationparty.com/#6827987</p></htmltext>
<tokenext>The translator ca n't seem to figure out exactly how many times the road has diverged... " two roads diverged in a yellow wood " http : //translationparty.com/ # 6827987</tokentext>
<sentencetext>The translator can't seem to figure out exactly how many times the road has diverged..."two roads diverged in a yellow wood"http://translationparty.com/#6827987</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422060</id>
	<title>How different is this from AI research?</title>
	<author>Anonymous</author>
	<datestamp>1268146020000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>1</modscore>
	<htmltext><p>Obligatory <a href="http://en.wikipedia.org/wiki/Chinese\_room" title="wikipedia.org" rel="nofollow">Chinese Room</a> [wikipedia.org] mention.</p><p>If a translation engine grows strong enough to adequately translate the phrases "give us our daily bread," "sharks are predatory carnivores," and "the loan shark wants his bread," that implies a significant ability to contextually infer meaning.  Could someone opine on (or point to a work exploring) how similar the task of building an accurate translator is to the task of building a competent, world-aware (if perhaps not absolutely Turing-quality) AI?</p></htmltext>
<tokenext>Obligatory Chinese Room [ wikipedia.org ] mention.If a translation engine grows strong enough to adequately translate the phrases " give us our daily bread , " " sharks are predatory carnivores , " and " the loan shark wants his bread , " that implies a significant ability to contextually infer meaning .
Could someone opine on ( or point to a work exploring ) how similar the task of building an accurate translator is to the task of building a competent , world-aware ( if perhaps not absolutely Turing-quality ) AI ?</tokentext>
<sentencetext>Obligatory Chinese Room [wikipedia.org] mention.If a translation engine grows strong enough to adequately translate the phrases "give us our daily bread," "sharks are predatory carnivores," and "the loan shark wants his bread," that implies a significant ability to contextually infer meaning.
Could someone opine on (or point to a work exploring) how similar the task of building an accurate translator is to the task of building a competent, world-aware (if perhaps not absolutely Turing-quality) AI?</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</id>
	<title>Converting that article from English to Chinese to</title>
	<author>Rei</author>
	<datestamp>1268139180000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>5</modscore>
	<htmltext><p>English, with Google Translate:</p><p>---<br>Google's rapid rise to the translation of business executives is a result of what Google released a complex problem, and its powerful computing power for reminding me. The data center, and its Web search, it may be now, when attacked with the network, is the world's largest computer. Google's machine translation technology is being used to push forward the limit. Last month, for example, it indicated that it was a combination of image analysis of the translation tools to enable a person, says that while walking in the German mobile phone menu, photos and immediately the English translation.<nobr> <wbr></nobr>... In the mid-90s, researchers began to favor a so-called statistical methods. They found that if they ate the computer or hundreds of thousands of millions of paragraphs and the translation of humans, it can learn how to make an accurate translation of the new text of speculation. Facts have proved that this technology requires large amounts of data and a lot of computing power, is the right of Google's alley.<nobr> <wbr></nobr>... Google's service is sufficient to convey the essence of news articles, it has become a quick translation of millions of people everywhere.<br>---</p><p>Okay, perhaps not spectacular... but compared to Babelfish:</p><p>---<nobr> <wbr></nobr>...Is anything the prompt possible to occur to the translation business's crown trapezoid's Google quick rise, when Google unties it when the complex question violence computing power. Perhaps the data central network it for the net search establishment now is, when attacks together, world large-scale computer. Google uses that machine to push in the translation technology limit. The previous month, for example, it said that it operates and the image analysis unifies its translation tool, allows the human to adopt a menu the handset picture and obtains one with German immediately English translation.<nobr> <wbr></nobr>... in the mid-1990s, researcher started to favor the so-called statistical method. They have discovered that if they have fed the translation which the computer thousands or the tens of thousands of paragraphs and their person cause, its possibly academic society does about what kind of guesses translator accurately the new text. \_ it this technology, requests the huge large amount data finally and completely the calculated horsepower, is correct Google the alley.<nobr> <wbr></nobr>... The Google service is enough good expresses the news article the essence, and it has become translation quick origin tens of thousands of people<br>---</p></htmltext>
<tokenext>English , with Google Translate : ---Google 's rapid rise to the translation of business executives is a result of what Google released a complex problem , and its powerful computing power for reminding me .
The data center , and its Web search , it may be now , when attacked with the network , is the world 's largest computer .
Google 's machine translation technology is being used to push forward the limit .
Last month , for example , it indicated that it was a combination of image analysis of the translation tools to enable a person , says that while walking in the German mobile phone menu , photos and immediately the English translation .
... In the mid-90s , researchers began to favor a so-called statistical methods .
They found that if they ate the computer or hundreds of thousands of millions of paragraphs and the translation of humans , it can learn how to make an accurate translation of the new text of speculation .
Facts have proved that this technology requires large amounts of data and a lot of computing power , is the right of Google 's alley .
... Google 's service is sufficient to convey the essence of news articles , it has become a quick translation of millions of people everywhere.---Okay , perhaps not spectacular... but compared to Babelfish : --- ...Is anything the prompt possible to occur to the translation business 's crown trapezoid 's Google quick rise , when Google unties it when the complex question violence computing power .
Perhaps the data central network it for the net search establishment now is , when attacks together , world large-scale computer .
Google uses that machine to push in the translation technology limit .
The previous month , for example , it said that it operates and the image analysis unifies its translation tool , allows the human to adopt a menu the handset picture and obtains one with German immediately English translation .
... in the mid-1990s , researcher started to favor the so-called statistical method .
They have discovered that if they have fed the translation which the computer thousands or the tens of thousands of paragraphs and their person cause , its possibly academic society does about what kind of guesses translator accurately the new text .
\ _ it this technology , requests the huge large amount data finally and completely the calculated horsepower , is correct Google the alley .
... The Google service is enough good expresses the news article the essence , and it has become translation quick origin tens of thousands of people---</tokentext>
<sentencetext>English, with Google Translate:---Google's rapid rise to the translation of business executives is a result of what Google released a complex problem, and its powerful computing power for reminding me.
The data center, and its Web search, it may be now, when attacked with the network, is the world's largest computer.
Google's machine translation technology is being used to push forward the limit.
Last month, for example, it indicated that it was a combination of image analysis of the translation tools to enable a person, says that while walking in the German mobile phone menu, photos and immediately the English translation.
... In the mid-90s, researchers began to favor a so-called statistical methods.
They found that if they ate the computer or hundreds of thousands of millions of paragraphs and the translation of humans, it can learn how to make an accurate translation of the new text of speculation.
Facts have proved that this technology requires large amounts of data and a lot of computing power, is the right of Google's alley.
... Google's service is sufficient to convey the essence of news articles, it has become a quick translation of millions of people everywhere.---Okay, perhaps not spectacular... but compared to Babelfish:--- ...Is anything the prompt possible to occur to the translation business's crown trapezoid's Google quick rise, when Google unties it when the complex question violence computing power.
Perhaps the data central network it for the net search establishment now is, when attacks together, world large-scale computer.
Google uses that machine to push in the translation technology limit.
The previous month, for example, it said that it operates and the image analysis unifies its translation tool, allows the human to adopt a menu the handset picture and obtains one with German immediately English translation.
... in the mid-1990s, researcher started to favor the so-called statistical method.
They have discovered that if they have fed the translation which the computer thousands or the tens of thousands of paragraphs and their person cause, its possibly academic society does about what kind of guesses translator accurately the new text.
\_ it this technology, requests the huge large amount data finally and completely the calculated horsepower, is correct Google the alley.
... The Google service is enough good expresses the news article the essence, and it has become translation quick origin tens of thousands of people---</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</id>
	<title>Re:Similar languages</title>
	<author>MBCook</author>
	<datestamp>1268141100000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>4</modscore>
	<htmltext><p>This seems like the ideal opportunity to mention <a href="http://translationparty.com/#6820339" title="translationparty.com">Translation Party</a> [translationparty.com]. You give it English, and it translates it to and back from Japanese until the input and output English are the same.
</p><p>It can be a ton of fun.</p></htmltext>
<tokenext>This seems like the ideal opportunity to mention Translation Party [ translationparty.com ] .
You give it English , and it translates it to and back from Japanese until the input and output English are the same .
It can be a ton of fun .</tokentext>
<sentencetext>This seems like the ideal opportunity to mention Translation Party [translationparty.com].
You give it English, and it translates it to and back from Japanese until the input and output English are the same.
It can be a ton of fun.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31438480</id>
	<title>Ob. Lebowski</title>
	<author>MrEd</author>
	<datestamp>1268326200000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p><a href="http://translationparty.com/#6848767" title="translationparty.com">Good times.</a> [translationparty.com]</p><p>"But sometimes, there's a man &ndash; and I'm talking about the Dude here &ndash; sometimes, there's a man, well, he's the man for his time and place. He fits right in there. And that's the Dude. In Los Angeles."</p><p>"But sometimes, man - you can go anywhere - even in some cases, men, men of his time and place. He is the right fit. Order. In Los Angeles."</p></htmltext>
<tokenext>Good times .
[ translationparty.com ] " But sometimes , there 's a man    and I 'm talking about the Dude here    sometimes , there 's a man , well , he 's the man for his time and place .
He fits right in there .
And that 's the Dude .
In Los Angeles .
" " But sometimes , man - you can go anywhere - even in some cases , men , men of his time and place .
He is the right fit .
Order. In Los Angeles .
"</tokentext>
<sentencetext>Good times.
[translationparty.com]"But sometimes, there's a man – and I'm talking about the Dude here – sometimes, there's a man, well, he's the man for his time and place.
He fits right in there.
And that's the Dude.
In Los Angeles.
""But sometimes, man - you can go anywhere - even in some cases, men, men of his time and place.
He is the right fit.
Order. In Los Angeles.
"</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421682</id>
	<title>Asian languages and vastly different grammar</title>
	<author>Anonymous</author>
	<datestamp>1268142780000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>5</modscore>
	<htmltext><p>Several others have noted this as well - for Asian languages, Google has a lot of work to do. The Chinese translation near the top is impressive, but while Chinese and Japanese translations are probably pretty good on Google, other Asian languages suffer greatly.</p><p>I've been translating a lot of Thai lately, and initially I thought Google was great - the interface is really slick, and it seemed to give a decent result. Passing the translation back through often gave me really weird stuff, but I was expecting that. So it was great, until I tried using it to communicate with someone in Thai - even for really, really basic stuff, often they had absolutely no idea. It was just way off.</p><p>While you can feed western languages through it and get great, usable results, for Asian languages besides Chinese and Japanese it's next to useless. I'm guessing there isn't much of an incentive for Google to focus on other Asian languages - for example, in Android 2.1 on the Nexus One there is no way to even install fonts for less-popular Asian scripts like Thai, much less inputting text in those scripts - despite this capability being available on certain other Android phones (you can install it on the Nexus One if you root it, of course).</p><p>Based on what their technique for learning translation is, though, hopefully this will improve over time. It's an impressive system as it is, but very much limited to "popular" languages and those very similar to English.</p></htmltext>
<tokenext>Several others have noted this as well - for Asian languages , Google has a lot of work to do .
The Chinese translation near the top is impressive , but while Chinese and Japanese translations are probably pretty good on Google , other Asian languages suffer greatly.I 've been translating a lot of Thai lately , and initially I thought Google was great - the interface is really slick , and it seemed to give a decent result .
Passing the translation back through often gave me really weird stuff , but I was expecting that .
So it was great , until I tried using it to communicate with someone in Thai - even for really , really basic stuff , often they had absolutely no idea .
It was just way off.While you can feed western languages through it and get great , usable results , for Asian languages besides Chinese and Japanese it 's next to useless .
I 'm guessing there is n't much of an incentive for Google to focus on other Asian languages - for example , in Android 2.1 on the Nexus One there is no way to even install fonts for less-popular Asian scripts like Thai , much less inputting text in those scripts - despite this capability being available on certain other Android phones ( you can install it on the Nexus One if you root it , of course ) .Based on what their technique for learning translation is , though , hopefully this will improve over time .
It 's an impressive system as it is , but very much limited to " popular " languages and those very similar to English .</tokentext>
<sentencetext>Several others have noted this as well - for Asian languages, Google has a lot of work to do.
The Chinese translation near the top is impressive, but while Chinese and Japanese translations are probably pretty good on Google, other Asian languages suffer greatly.I've been translating a lot of Thai lately, and initially I thought Google was great - the interface is really slick, and it seemed to give a decent result.
Passing the translation back through often gave me really weird stuff, but I was expecting that.
So it was great, until I tried using it to communicate with someone in Thai - even for really, really basic stuff, often they had absolutely no idea.
It was just way off.While you can feed western languages through it and get great, usable results, for Asian languages besides Chinese and Japanese it's next to useless.
I'm guessing there isn't much of an incentive for Google to focus on other Asian languages - for example, in Android 2.1 on the Nexus One there is no way to even install fonts for less-popular Asian scripts like Thai, much less inputting text in those scripts - despite this capability being available on certain other Android phones (you can install it on the Nexus One if you root it, of course).Based on what their technique for learning translation is, though, hopefully this will improve over time.
It's an impressive system as it is, but very much limited to "popular" languages and those very similar to English.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424792</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>Anonymous</author>
	<datestamp>1268226720000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext>It's not called Babblefish without a reason.</htmltext>
<tokenext>It 's not called Babblefish without a reason .</tokentext>
<sentencetext>It's not called Babblefish without a reason.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424522</id>
	<title>Potential As A Learning Tool?</title>
	<author>RavenousBlack</author>
	<datestamp>1268221740000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Lately I've been trying out using Google Translate to improve my German. Whenever I write a sentence that I'm not too sure about, I take my English version of it and translate it into German in Google to see how it compares. So far it's been useful in better understanding preposition usage and sentence structure. That is, if it's reliable enough.</htmltext>
<tokenext>Lately I 've been trying out using Google Translate to improve my German .
Whenever I write a sentence that I 'm not too sure about , I take my English version of it and translate it into German in Google to see how it compares .
So far it 's been useful in better understanding preposition usage and sentence structure .
That is , if it 's reliable enough .</tokentext>
<sentencetext>Lately I've been trying out using Google Translate to improve my German.
Whenever I write a sentence that I'm not too sure about, I take my English version of it and translate it into German in Google to see how it compares.
So far it's been useful in better understanding preposition usage and sentence structure.
That is, if it's reliable enough.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423132</id>
	<title>Re:Asian languages and vastly different grammar</title>
	<author>Anonymous</author>
	<datestamp>1268157240000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>Ah, from English / from Chinese to Japanese both sucks. I've just confirmed it. For years Chinese to English is known to work well as Europe and China are on the same continent and share basic structure of languages. Japanese is a slightly different stuff and we got a bit more to do......</p><p>giving <a href="http://chinese.engadget.com/2010/03/09/samsung-prices-tl500-tl350-aq100-and-sl605-shooters/" title="engadget.com" rel="nofollow">http://chinese.engadget.com/2010/03/09/samsung-prices-tl500-tl350-aq100-and-sl605-shooters/</a> [engadget.com] will return unreadable Japanese, if  I'd translate it to English that'd be something like:</p><p><div class="quote"><p>timesamsung TL500TL350AQ100 and SL605, yet to talked on price for telling everything, announced previous. Especially, also TL500, when walks like Ricoh Loewe System, Pana LX3, small size will, specification, like hot-shoe line of strong strobe. Someone, itch inside my mind, at very last what level of price curious about, saw this digital camera? current sentence will be given. 14300 of NT is about 449 dollars, asks price. TL350 349 dollars or so. Not only TL500 and TL350, double shake-reduction has RAW format.</p></div></div>
	</htmltext>
<tokenext>Ah , from English / from Chinese to Japanese both sucks .
I 've just confirmed it .
For years Chinese to English is known to work well as Europe and China are on the same continent and share basic structure of languages .
Japanese is a slightly different stuff and we got a bit more to do......giving http : //chinese.engadget.com/2010/03/09/samsung-prices-tl500-tl350-aq100-and-sl605-shooters/ [ engadget.com ] will return unreadable Japanese , if I 'd translate it to English that 'd be something like : timesamsung TL500TL350AQ100 and SL605 , yet to talked on price for telling everything , announced previous .
Especially , also TL500 , when walks like Ricoh Loewe System , Pana LX3 , small size will , specification , like hot-shoe line of strong strobe .
Someone , itch inside my mind , at very last what level of price curious about , saw this digital camera ?
current sentence will be given .
14300 of NT is about 449 dollars , asks price .
TL350 349 dollars or so .
Not only TL500 and TL350 , double shake-reduction has RAW format .</tokentext>
<sentencetext>Ah, from English / from Chinese to Japanese both sucks.
I've just confirmed it.
For years Chinese to English is known to work well as Europe and China are on the same continent and share basic structure of languages.
Japanese is a slightly different stuff and we got a bit more to do......giving http://chinese.engadget.com/2010/03/09/samsung-prices-tl500-tl350-aq100-and-sl605-shooters/ [engadget.com] will return unreadable Japanese, if  I'd translate it to English that'd be something like:timesamsung TL500TL350AQ100 and SL605, yet to talked on price for telling everything, announced previous.
Especially, also TL500, when walks like Ricoh Loewe System, Pana LX3, small size will, specification, like hot-shoe line of strong strobe.
Someone, itch inside my mind, at very last what level of price curious about, saw this digital camera?
current sentence will be given.
14300 of NT is about 449 dollars, asks price.
TL350 349 dollars or so.
Not only TL500 and TL350, double shake-reduction has RAW format.
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421682</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423304</id>
	<title>Re:Why is machine translation so difficult?</title>
	<author>BZ</author>
	<datestamp>1268159280000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Yes, it really is that difficult.  Consider this classic example in English:</p><p>
&nbsp; &nbsp; Time flies like an arrow.<br>
&nbsp; &nbsp; Fruit flies like a banana.</p><p>There happen to be two ways to read the latter sentence.  One is in a way analogous to the former one: the subject is "Fruit", the intransitive verb is "flies", and "like a banana" is an adverb phrase.  The other way to read it is that the subject is the noun phrase "Fruit flies" , the transitice verb is "like" and the direct object is "a banana".  Heck, this case is difficult for \_humans\_ to get "right" at times.</p><p>There are various situations like that in which the meaning is ambiguous, but even worse are situations in which the concepts used are just nonexistent in one of the languages/cultures.  For example, English names are made up of three parts, typically: first, middle, last.  Russian names are also made up of three parts: given, patronymic, family.  Russian family name is a good match for English last name.  Russian given name is a good match for English first name.  Russian patronymic is<nobr> <wbr></nobr>... not really a match for English middle name (in that for example it's not up to the parents to choose it), but occupies a similar position in names, obviously.</p><p>So when translating a phrase containing  (patronymic) into English, what word you use to translate it really needs to depend on what's being said.  If it's a technical discussion about the concept, translate as "patronymic".  If it's a casual discussion about names, "middle name" may be appropriate.  If the Russian text says that X addressed Y by name and patronymic then that \_is\_ what they did, but that happens to be the standard polite form of address.  The equivalent English form is a Mr/Mrs/whatever followed by the last name, and the translation should reflect that.</p><p>There are also often situations in which two phrases are technically the same in terms of denotation but have different connotations (or heck, just different emphasis on which words are important; compare "I <em>saw</em> him" to "I saw <em>him/em" and note that such emphasis differences can be expressed with word order in many languages).  Getting that right can be very difficult unless you really understand what's being said.  Pattern matching might work if you've seen that exact pattern before (which is Google's approach), but even small differences in the surrounding sentence structure can totally change the meaning of the part you're trying to translate.</em></p><p><em>I leave you with this short story (or rather stories):</em></p><p><em>
&nbsp; &nbsp; Jack was walking across the meadow when he saw a spring.  The spring glinted in the<br>
&nbsp; &nbsp; sunlight, and he thought that he'd never seen something quite so beautiful.  He bent<br>
&nbsp; &nbsp; down and...</em></p><p><em>
&nbsp; &nbsp; 1)<nobr> <wbr></nobr>... put it in his pocket.<br>
&nbsp; &nbsp; 2)<nobr> <wbr></nobr>... had a drink.</em></p><p><em>How much lookahead in the translation is needed to translate the first sentence correctly?  If the rest of the story is option 2 above, how do you know that he didn't just take a swig from his flask before picking up the bit of metal?</em></p></htmltext>
<tokenext>Yes , it really is that difficult .
Consider this classic example in English :     Time flies like an arrow .
    Fruit flies like a banana.There happen to be two ways to read the latter sentence .
One is in a way analogous to the former one : the subject is " Fruit " , the intransitive verb is " flies " , and " like a banana " is an adverb phrase .
The other way to read it is that the subject is the noun phrase " Fruit flies " , the transitice verb is " like " and the direct object is " a banana " .
Heck , this case is difficult for \ _humans \ _ to get " right " at times.There are various situations like that in which the meaning is ambiguous , but even worse are situations in which the concepts used are just nonexistent in one of the languages/cultures .
For example , English names are made up of three parts , typically : first , middle , last .
Russian names are also made up of three parts : given , patronymic , family .
Russian family name is a good match for English last name .
Russian given name is a good match for English first name .
Russian patronymic is ... not really a match for English middle name ( in that for example it 's not up to the parents to choose it ) , but occupies a similar position in names , obviously.So when translating a phrase containing ( patronymic ) into English , what word you use to translate it really needs to depend on what 's being said .
If it 's a technical discussion about the concept , translate as " patronymic " .
If it 's a casual discussion about names , " middle name " may be appropriate .
If the Russian text says that X addressed Y by name and patronymic then that \ _is \ _ what they did , but that happens to be the standard polite form of address .
The equivalent English form is a Mr/Mrs/whatever followed by the last name , and the translation should reflect that.There are also often situations in which two phrases are technically the same in terms of denotation but have different connotations ( or heck , just different emphasis on which words are important ; compare " I saw him " to " I saw him/em " and note that such emphasis differences can be expressed with word order in many languages ) .
Getting that right can be very difficult unless you really understand what 's being said .
Pattern matching might work if you 've seen that exact pattern before ( which is Google 's approach ) , but even small differences in the surrounding sentence structure can totally change the meaning of the part you 're trying to translate.I leave you with this short story ( or rather stories ) :     Jack was walking across the meadow when he saw a spring .
The spring glinted in the     sunlight , and he thought that he 'd never seen something quite so beautiful .
He bent     down and.. .     1 ) ... put it in his pocket .
    2 ) ... had a drink.How much lookahead in the translation is needed to translate the first sentence correctly ?
If the rest of the story is option 2 above , how do you know that he did n't just take a swig from his flask before picking up the bit of metal ?</tokentext>
<sentencetext>Yes, it really is that difficult.
Consider this classic example in English:
    Time flies like an arrow.
    Fruit flies like a banana.There happen to be two ways to read the latter sentence.
One is in a way analogous to the former one: the subject is "Fruit", the intransitive verb is "flies", and "like a banana" is an adverb phrase.
The other way to read it is that the subject is the noun phrase "Fruit flies" , the transitice verb is "like" and the direct object is "a banana".
Heck, this case is difficult for \_humans\_ to get "right" at times.There are various situations like that in which the meaning is ambiguous, but even worse are situations in which the concepts used are just nonexistent in one of the languages/cultures.
For example, English names are made up of three parts, typically: first, middle, last.
Russian names are also made up of three parts: given, patronymic, family.
Russian family name is a good match for English last name.
Russian given name is a good match for English first name.
Russian patronymic is ... not really a match for English middle name (in that for example it's not up to the parents to choose it), but occupies a similar position in names, obviously.So when translating a phrase containing  (patronymic) into English, what word you use to translate it really needs to depend on what's being said.
If it's a technical discussion about the concept, translate as "patronymic".
If it's a casual discussion about names, "middle name" may be appropriate.
If the Russian text says that X addressed Y by name and patronymic then that \_is\_ what they did, but that happens to be the standard polite form of address.
The equivalent English form is a Mr/Mrs/whatever followed by the last name, and the translation should reflect that.There are also often situations in which two phrases are technically the same in terms of denotation but have different connotations (or heck, just different emphasis on which words are important; compare "I saw him" to "I saw him/em" and note that such emphasis differences can be expressed with word order in many languages).
Getting that right can be very difficult unless you really understand what's being said.
Pattern matching might work if you've seen that exact pattern before (which is Google's approach), but even small differences in the surrounding sentence structure can totally change the meaning of the part you're trying to translate.I leave you with this short story (or rather stories):
    Jack was walking across the meadow when he saw a spring.
The spring glinted in the
    sunlight, and he thought that he'd never seen something quite so beautiful.
He bent
    down and...
    1) ... put it in his pocket.
    2) ... had a drink.How much lookahead in the translation is needed to translate the first sentence correctly?
If the rest of the story is option 2 above, how do you know that he didn't just take a swig from his flask before picking up the bit of metal?</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31425006</id>
	<title>Re:Their search parsing tech probably helps too</title>
	<author>Anonymous</author>
	<datestamp>1268229840000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>pretty standard stuff within the Natural Language Processing community, except they do it large-scale.</p><p>plus, these things are *not* used in translation systems.</p></htmltext>
<tokenext>pretty standard stuff within the Natural Language Processing community , except they do it large-scale.plus , these things are * not * used in translation systems .</tokentext>
<sentencetext>pretty standard stuff within the Natural Language Processing community, except they do it large-scale.plus, these things are *not* used in translation systems.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421488</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423244</id>
	<title>Low-volume languages?</title>
	<author>vampire\_baozi</author>
	<datestamp>1268158560000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>While this works well for the more widely-spoken languages (Western/European Languages, Chinese, Japanese), I suspect there is a massive drop-off for some of the less common languages, especially those for languages spoken in countries less connected to the internet.  The article mentioned they feed the algorithm human translations from the EU and UN proceedings; what about less-common Asian languages, the Indian subcontinent languages, central Asian languages?  The volume simply doesn't exist.<br>Where the volume does exist, what about Russian and Korean, which are dominated by Yandex and Naver? Might be interesting to run a comparison, but unfortunately all the languages I speak are covered fairly well by Google at this point<nobr> <wbr></nobr>:(</p></htmltext>
<tokenext>While this works well for the more widely-spoken languages ( Western/European Languages , Chinese , Japanese ) , I suspect there is a massive drop-off for some of the less common languages , especially those for languages spoken in countries less connected to the internet .
The article mentioned they feed the algorithm human translations from the EU and UN proceedings ; what about less-common Asian languages , the Indian subcontinent languages , central Asian languages ?
The volume simply does n't exist.Where the volume does exist , what about Russian and Korean , which are dominated by Yandex and Naver ?
Might be interesting to run a comparison , but unfortunately all the languages I speak are covered fairly well by Google at this point : (</tokentext>
<sentencetext>While this works well for the more widely-spoken languages (Western/European Languages, Chinese, Japanese), I suspect there is a massive drop-off for some of the less common languages, especially those for languages spoken in countries less connected to the internet.
The article mentioned they feed the algorithm human translations from the EU and UN proceedings; what about less-common Asian languages, the Indian subcontinent languages, central Asian languages?
The volume simply doesn't exist.Where the volume does exist, what about Russian and Korean, which are dominated by Yandex and Naver?
Might be interesting to run a comparison, but unfortunately all the languages I speak are covered fairly well by Google at this point :(</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421202</id>
	<title>Not from NY Times</title>
	<author>Anonymous</author>
	<datestamp>1268139660000</datestamp>
	<modclass>Informativ</modclass>
	<modscore>3</modscore>
	<htmltext><p>Last week's The Economist adressed this issue (http://www.economist.com/specialreports/displaystory.cfm?story\_id=15557431).  NY Times recycled it</p></htmltext>
<tokenext>Last week 's The Economist adressed this issue ( http : //www.economist.com/specialreports/displaystory.cfm ? story \ _id = 15557431 ) .
NY Times recycled it</tokentext>
<sentencetext>Last week's The Economist adressed this issue (http://www.economist.com/specialreports/displaystory.cfm?story\_id=15557431).
NY Times recycled it</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424278</id>
	<title>Re:Their search parsing tech probably helps too</title>
	<author>DollyTheSheep</author>
	<datestamp>1268217720000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p><div class="quote"><p>Wired recently had <a href="http://www.wired.com/magazine/2010/02/ff\_google\_algorithm" title="wired.com" rel="nofollow">this article</a> [wired.com] on Google's search algorithm, which mentioned how far ahead it was in parsing language for things like bi-grams to figure out what the meaning of the search was by "figuring out" the relationships between related words in a very human-like way. They have also built an impressive synonym system. These technologies, developed for search, strike me as really critical for good translation.</p></div><p>OK, so they introduced contextual knowledge (or "world knowledge" or "semantics" if you will) when they saw, that page rank and keyword based search didn't cut it for many search queries? Shouldn't that have come not as an afterthought but long before? I mean, how can anyone expect, that search would never involve some contextual knowledge to be succesful?</p><p>My guess is, that Google of course knows this. What they do is to build up contextual knowledge through their own search engine, how people relate words to each other and not by imposing a predefined rule set or ontolgy beforehand like <a href="http://en.wikipedia.org/wiki/Cyc" title="wikipedia.org" rel="nofollow">cyc</a> [wikipedia.org] </p><p>.</p></div>
	</htmltext>
<tokenext>Wired recently had this article [ wired.com ] on Google 's search algorithm , which mentioned how far ahead it was in parsing language for things like bi-grams to figure out what the meaning of the search was by " figuring out " the relationships between related words in a very human-like way .
They have also built an impressive synonym system .
These technologies , developed for search , strike me as really critical for good translation.OK , so they introduced contextual knowledge ( or " world knowledge " or " semantics " if you will ) when they saw , that page rank and keyword based search did n't cut it for many search queries ?
Should n't that have come not as an afterthought but long before ?
I mean , how can anyone expect , that search would never involve some contextual knowledge to be succesful ? My guess is , that Google of course knows this .
What they do is to build up contextual knowledge through their own search engine , how people relate words to each other and not by imposing a predefined rule set or ontolgy beforehand like cyc [ wikipedia.org ] .</tokentext>
<sentencetext>Wired recently had this article [wired.com] on Google's search algorithm, which mentioned how far ahead it was in parsing language for things like bi-grams to figure out what the meaning of the search was by "figuring out" the relationships between related words in a very human-like way.
They have also built an impressive synonym system.
These technologies, developed for search, strike me as really critical for good translation.OK, so they introduced contextual knowledge (or "world knowledge" or "semantics" if you will) when they saw, that page rank and keyword based search didn't cut it for many search queries?
Shouldn't that have come not as an afterthought but long before?
I mean, how can anyone expect, that search would never involve some contextual knowledge to be succesful?My guess is, that Google of course knows this.
What they do is to build up contextual knowledge through their own search engine, how people relate words to each other and not by imposing a predefined rule set or ontolgy beforehand like cyc [wikipedia.org] .
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421488</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423374</id>
	<title>Try iSnapit and translate</title>
	<author>billwallace</author>
	<datestamp>1268160540000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Try iSnapit on your iPhone or Android, and you can translate everything you see with a single click - and much more.</htmltext>
<tokenext>Try iSnapit on your iPhone or Android , and you can translate everything you see with a single click - and much more .</tokentext>
<sentencetext>Try iSnapit on your iPhone or Android, and you can translate everything you see with a single click - and much more.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421406</id>
	<title>For western languages...</title>
	<author>Anonymous</author>
	<datestamp>1268140980000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>2</modscore>
	<htmltext>For western languages, I have no doubt that this will eventually be a decent option for general text.
<p>
Just not now.  It still needs a lot of work.
</p><p>
I'm in the translation business, and the general trend in internet communications such as websites, etc. at least, is to simplify the language being used.
</p><p>
For specialized text, we're a <i> long</i> way off yet.</p></htmltext>
<tokenext>For western languages , I have no doubt that this will eventually be a decent option for general text .
Just not now .
It still needs a lot of work .
I 'm in the translation business , and the general trend in internet communications such as websites , etc .
at least , is to simplify the language being used .
For specialized text , we 're a long way off yet .</tokentext>
<sentencetext>For western languages, I have no doubt that this will eventually be a decent option for general text.
Just not now.
It still needs a lot of work.
I'm in the translation business, and the general trend in internet communications such as websites, etc.
at least, is to simplify the language being used.
For specialized text, we're a  long way off yet.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423604</id>
	<title>nokia had this years ago</title>
	<author>dwater</author>
	<datestamp>1268251980000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>I guess what Google is talking about must be something different because Nokia had s/w for the N95 that could take a picture of a Chinese menu and provide a translation in English.</p></htmltext>
<tokenext>I guess what Google is talking about must be something different because Nokia had s/w for the N95 that could take a picture of a Chinese menu and provide a translation in English .</tokentext>
<sentencetext>I guess what Google is talking about must be something different because Nokia had s/w for the N95 that could take a picture of a Chinese menu and provide a translation in English.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31426530</id>
	<title>Not that different from AI in some ways</title>
	<author>daemonenwind</author>
	<datestamp>1268238240000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>There are 2 core problems with translating:<br>1.  Language requires a cultural frame of reference.<br>You can see this in understanding humor in different societies.  For example Monty Python is a product of a British perspective.  The English language, as spoken in England, only works when you understand the culture behind it.  For example, "daily bread" only works in western languages because of the shared Christian influence.  In Japanese, for example, "daily rice" might bring up a similar understanding that "daily bread" doesn't carry.</p><p>2.  Language is a moving target.<br>References keep changing, and a computer (or even a foreign-based translator) has a hard time keeping up.  Think about what Tea Party meant just 5 years ago, as opposed to today.</p><p>All this means that you're going to get a really good computer translator about the time you get a really good computer painter.  Even the best of the given translations in the responses to this story aren't anything someone would want to publish as an example of good English usage - the only benefit is a moderate ability to get the point of the subject.</p><p>Or to drive the point home, try passing Goethe through the translator and see if the English is as good as the German.<br>That's the true test of a translator - can it retain excellence, beyond base meaning?</p><p>example:<br>Wenn ein Edler gegen dich fehlt, so tu als h&#228;ttest dus nicht gez&#228;hlt!<nobr> <wbr></nobr>..... Er wird es in sein Schuldbuch schreiben und dir nicht lange im Gebet bleiben.</p><p>becomes<br>When the gentleman wanting against you, then do as you would not have counted's!<nobr> <wbr></nobr>..... He will write it in his book of guilt and you do not stay long in prayer.</p><p>Sure you get the idea, but the artistry is pure fail.</p></htmltext>
<tokenext>There are 2 core problems with translating : 1 .
Language requires a cultural frame of reference.You can see this in understanding humor in different societies .
For example Monty Python is a product of a British perspective .
The English language , as spoken in England , only works when you understand the culture behind it .
For example , " daily bread " only works in western languages because of the shared Christian influence .
In Japanese , for example , " daily rice " might bring up a similar understanding that " daily bread " does n't carry.2 .
Language is a moving target.References keep changing , and a computer ( or even a foreign-based translator ) has a hard time keeping up .
Think about what Tea Party meant just 5 years ago , as opposed to today.All this means that you 're going to get a really good computer translator about the time you get a really good computer painter .
Even the best of the given translations in the responses to this story are n't anything someone would want to publish as an example of good English usage - the only benefit is a moderate ability to get the point of the subject.Or to drive the point home , try passing Goethe through the translator and see if the English is as good as the German.That 's the true test of a translator - can it retain excellence , beyond base meaning ? example : Wenn ein Edler gegen dich fehlt , so tu als h   ttest dus nicht gez   hlt !
..... Er wird es in sein Schuldbuch schreiben und dir nicht lange im Gebet bleiben.becomesWhen the gentleman wanting against you , then do as you would not have counted 's !
..... He will write it in his book of guilt and you do not stay long in prayer.Sure you get the idea , but the artistry is pure fail .</tokentext>
<sentencetext>There are 2 core problems with translating:1.
Language requires a cultural frame of reference.You can see this in understanding humor in different societies.
For example Monty Python is a product of a British perspective.
The English language, as spoken in England, only works when you understand the culture behind it.
For example, "daily bread" only works in western languages because of the shared Christian influence.
In Japanese, for example, "daily rice" might bring up a similar understanding that "daily bread" doesn't carry.2.
Language is a moving target.References keep changing, and a computer (or even a foreign-based translator) has a hard time keeping up.
Think about what Tea Party meant just 5 years ago, as opposed to today.All this means that you're going to get a really good computer translator about the time you get a really good computer painter.
Even the best of the given translations in the responses to this story aren't anything someone would want to publish as an example of good English usage - the only benefit is a moderate ability to get the point of the subject.Or to drive the point home, try passing Goethe through the translator and see if the English is as good as the German.That's the true test of a translator - can it retain excellence, beyond base meaning?example:Wenn ein Edler gegen dich fehlt, so tu als hättest dus nicht gezählt!
..... Er wird es in sein Schuldbuch schreiben und dir nicht lange im Gebet bleiben.becomesWhen the gentleman wanting against you, then do as you would not have counted's!
..... He will write it in his book of guilt and you do not stay long in prayer.Sure you get the idea, but the artistry is pure fail.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422060</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31426078</id>
	<title>Re:Similar languages</title>
	<author>Anonymous</author>
	<datestamp>1268236380000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>Try this one:</p><p>http://translationparty.com/#6834010</p><p>Awesome hilarity ensue.</p></htmltext>
<tokenext>Try this one : http : //translationparty.com/ # 6834010Awesome hilarity ensue .</tokentext>
<sentencetext>Try this one:http://translationparty.com/#6834010Awesome hilarity ensue.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31430634</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>BikeHelmet</author>
	<datestamp>1268214000000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Keep in mind that the translation algo is most suited for regular grammar. Not the gobbledeegook it outputs. Grammar -&gt; Chinese gobbledeegook -&gt; English gobbledeegook is a pretty decent translation.</p></htmltext>
<tokenext>Keep in mind that the translation algo is most suited for regular grammar .
Not the gobbledeegook it outputs .
Grammar - &gt; Chinese gobbledeegook - &gt; English gobbledeegook is a pretty decent translation .</tokentext>
<sentencetext>Keep in mind that the translation algo is most suited for regular grammar.
Not the gobbledeegook it outputs.
Grammar -&gt; Chinese gobbledeegook -&gt; English gobbledeegook is a pretty decent translation.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421918</id>
	<title>Chess translations</title>
	<author>JordanH</author>
	<datestamp>1268145000000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>If you are into chess, Google Translate opens up a whole world of chess blogs to you.  I haven't used it extensively, but I was quite impressed with
<a href="http://translate.google.com/translate?hl=en&amp;sl=es&amp;tl=en&amp;u=http\%3A\%2F\%2Fcomentariosdeajedrez.blogspot.com\%2F2010\%2F02\%2Fhipermodernismo-y-centro-iii.html" title="google.com" rel="nofollow">this translation</a> [google.com].

</p><p>To the chess players out there, note how it picks up notation interspersed with the text.  It's not perfect and seems to fall back into Spanish algebraic in odd places, but I think they are the only translation tool that even tries to do chess notation.

</p><p>I wonder if there are other "special purpose" translations that Google Translate attempts.  It's pretty impressive to me that they even bother with the small chess blog reading public.

</p><p>Oh, Google Translate does a lot better job on the non-chess parts of blogs, too.</p></htmltext>
<tokenext>If you are into chess , Google Translate opens up a whole world of chess blogs to you .
I have n't used it extensively , but I was quite impressed with this translation [ google.com ] .
To the chess players out there , note how it picks up notation interspersed with the text .
It 's not perfect and seems to fall back into Spanish algebraic in odd places , but I think they are the only translation tool that even tries to do chess notation .
I wonder if there are other " special purpose " translations that Google Translate attempts .
It 's pretty impressive to me that they even bother with the small chess blog reading public .
Oh , Google Translate does a lot better job on the non-chess parts of blogs , too .</tokentext>
<sentencetext>If you are into chess, Google Translate opens up a whole world of chess blogs to you.
I haven't used it extensively, but I was quite impressed with
this translation [google.com].
To the chess players out there, note how it picks up notation interspersed with the text.
It's not perfect and seems to fall back into Spanish algebraic in odd places, but I think they are the only translation tool that even tries to do chess notation.
I wonder if there are other "special purpose" translations that Google Translate attempts.
It's pretty impressive to me that they even bother with the small chess blog reading public.
Oh, Google Translate does a lot better job on the non-chess parts of blogs, too.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421480</id>
	<title>I noticed that they were using my web site</title>
	<author>Anonymous</author>
	<datestamp>1268141400000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>2</modscore>
	<htmltext><p>I have a web site where every page is available in English and German. When I tested Google's translation with it, I noticed that Google reliably translated one sentence in the opposite direction, i.e. from English to German when I had asked for a German to English translation: On every page in German, there is one sentence in English which leads to the corresponding page in English. Google's translator appeared to pick the translation right from that page, which of course has that sentence in German (leading to the German version of that page). Google doesn't do this anymore, but when I saw it, I realized that Google's translator did not at all "understand" what it was translating.</p></htmltext>
<tokenext>I have a web site where every page is available in English and German .
When I tested Google 's translation with it , I noticed that Google reliably translated one sentence in the opposite direction , i.e .
from English to German when I had asked for a German to English translation : On every page in German , there is one sentence in English which leads to the corresponding page in English .
Google 's translator appeared to pick the translation right from that page , which of course has that sentence in German ( leading to the German version of that page ) .
Google does n't do this anymore , but when I saw it , I realized that Google 's translator did not at all " understand " what it was translating .</tokentext>
<sentencetext>I have a web site where every page is available in English and German.
When I tested Google's translation with it, I noticed that Google reliably translated one sentence in the opposite direction, i.e.
from English to German when I had asked for a German to English translation: On every page in German, there is one sentence in English which leads to the corresponding page in English.
Google's translator appeared to pick the translation right from that page, which of course has that sentence in German (leading to the German version of that page).
Google doesn't do this anymore, but when I saw it, I realized that Google's translator did not at all "understand" what it was translating.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421872</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>glwtta</author>
	<datestamp>1268144640000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>"I had a small house of brokerage on Wall Street... many days no business come to my hut, but Jimmy has fear?  A thousand times no.  I never doubted myself for a minute for I knew that my monkey strong bowels were girded with strength like the loins of a dragon ribboned with fat and the opulence of buffalo dung."</htmltext>
<tokenext>" I had a small house of brokerage on Wall Street... many days no business come to my hut , but Jimmy has fear ?
A thousand times no .
I never doubted myself for a minute for I knew that my monkey strong bowels were girded with strength like the loins of a dragon ribboned with fat and the opulence of buffalo dung .
"</tokentext>
<sentencetext>"I had a small house of brokerage on Wall Street... many days no business come to my hut, but Jimmy has fear?
A thousand times no.
I never doubted myself for a minute for I knew that my monkey strong bowels were girded with strength like the loins of a dragon ribboned with fat and the opulence of buffalo dung.
"</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31428086</id>
	<title>Re:I noticed that they were using my web site</title>
	<author>Anonymous</author>
	<datestamp>1268245200000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>You could translate all your pages using babblefish, and feed that to the google bot....</p></htmltext>
<tokenext>You could translate all your pages using babblefish , and feed that to the google bot... .</tokentext>
<sentencetext>You could translate all your pages using babblefish, and feed that to the google bot....</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421480</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31432766</id>
	<title>Re:Chess translations</title>
	<author>Aighearach</author>
	<datestamp>1268225580000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>That's really sweet, I'm a chess player and I really appreciate you pointing out this resource.</p><p>I don't think it needs a special purpose capability because it uses the web data in a more generic way and has lots of chess sites as data already.</p></htmltext>
<tokenext>That 's really sweet , I 'm a chess player and I really appreciate you pointing out this resource.I do n't think it needs a special purpose capability because it uses the web data in a more generic way and has lots of chess sites as data already .</tokentext>
<sentencetext>That's really sweet, I'm a chess player and I really appreciate you pointing out this resource.I don't think it needs a special purpose capability because it uses the web data in a more generic way and has lots of chess sites as data already.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421918</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422432</id>
	<title>Malay English dictionary</title>
	<author>Anonymous</author>
	<datestamp>1268150220000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>I have found in for Malay-English translations, that initially, Googles translation was better than Dewan Pustaka Dan Bahasa (DPDB) ie the people in charge of developing the Malay language. Since then however, I have found more errors creeping into their translations. I wonder if somebody is poisoning the well because when I first used Google translate the 99\% of the translations were accurate, and the 1\% was an unknown word. In my last use of Google translate, 50\% of the words were wrong (as opposed to being unknown).</p></htmltext>
<tokenext>I have found in for Malay-English translations , that initially , Googles translation was better than Dewan Pustaka Dan Bahasa ( DPDB ) ie the people in charge of developing the Malay language .
Since then however , I have found more errors creeping into their translations .
I wonder if somebody is poisoning the well because when I first used Google translate the 99 \ % of the translations were accurate , and the 1 \ % was an unknown word .
In my last use of Google translate , 50 \ % of the words were wrong ( as opposed to being unknown ) .</tokentext>
<sentencetext>I have found in for Malay-English translations, that initially, Googles translation was better than Dewan Pustaka Dan Bahasa (DPDB) ie the people in charge of developing the Malay language.
Since then however, I have found more errors creeping into their translations.
I wonder if somebody is poisoning the well because when I first used Google translate the 99\% of the translations were accurate, and the 1\% was an unknown word.
In my last use of Google translate, 50\% of the words were wrong (as opposed to being unknown).</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421732</id>
	<title>Pretty good and impressive as it translated</title>
	<author>al0ha</author>
	<datestamp>1268143320000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Eier von Satan correctly - except for Augenballgro&#223;e which is essentially Eye-ball-large.</htmltext>
<tokenext>Eier von Satan correctly - except for Augenballgro   e which is essentially Eye-ball-large .</tokentext>
<sentencetext>Eier von Satan correctly - except for Augenballgroße which is essentially Eye-ball-large.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424984</id>
	<title>If you're learning a language</title>
	<author>badzilla</author>
	<datestamp>1268229360000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>then Google Translate (or for some things wordreference.com) are fantastic resources. I don't mind that large chunks of text get translated in a stilted way - if you just need to get the meaning of a short phrase then Google is so much faster and easier than a paper dictionary.</p></htmltext>
<tokenext>then Google Translate ( or for some things wordreference.com ) are fantastic resources .
I do n't mind that large chunks of text get translated in a stilted way - if you just need to get the meaning of a short phrase then Google is so much faster and easier than a paper dictionary .</tokentext>
<sentencetext>then Google Translate (or for some things wordreference.com) are fantastic resources.
I don't mind that large chunks of text get translated in a stilted way - if you just need to get the meaning of a short phrase then Google is so much faster and easier than a paper dictionary.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31430790</id>
	<title>I'm not that impressed</title>
	<author>Anonymous</author>
	<datestamp>1268214780000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>I don't believe an entirely stochastic approach is the solution to the problem of correctly translating text between languages. Sure, Google does well at translating Spanish to English, but its translation from Russian to English is god-awful, and its translation of Kafka from German to English is lacking. The problem with stochastic is that it often neglects to include grammatical or morphological rules. The Russian translation example really brings this to light, as it translates perfective words poorly: "pokoncheno" (has ended) as "to end", and "ostonovleno" as "stopped" (rather than "has stopped").</p></htmltext>
<tokenext>I do n't believe an entirely stochastic approach is the solution to the problem of correctly translating text between languages .
Sure , Google does well at translating Spanish to English , but its translation from Russian to English is god-awful , and its translation of Kafka from German to English is lacking .
The problem with stochastic is that it often neglects to include grammatical or morphological rules .
The Russian translation example really brings this to light , as it translates perfective words poorly : " pokoncheno " ( has ended ) as " to end " , and " ostonovleno " as " stopped " ( rather than " has stopped " ) .</tokentext>
<sentencetext>I don't believe an entirely stochastic approach is the solution to the problem of correctly translating text between languages.
Sure, Google does well at translating Spanish to English, but its translation from Russian to English is god-awful, and its translation of Kafka from German to English is lacking.
The problem with stochastic is that it often neglects to include grammatical or morphological rules.
The Russian translation example really brings this to light, as it translates perfective words poorly: "pokoncheno" (has ended) as "to end", and "ostonovleno" as "stopped" (rather than "has stopped").</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423058</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>Anonymous</author>
	<datestamp>1268156280000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>this is what is dimensional analysis for physic:<br>given the maximum password length, determine the computing power of the provider:<br>example gmail.com, hotmail.com and others<br>tips: hashtables</p></htmltext>
<tokenext>this is what is dimensional analysis for physic : given the maximum password length , determine the computing power of the provider : example gmail.com , hotmail.com and otherstips : hashtables</tokentext>
<sentencetext>this is what is dimensional analysis for physic:given the maximum password length, determine the computing power of the provider:example gmail.com, hotmail.com and otherstips: hashtables</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423362</id>
	<title>Re:Asian languages and vastly different grammar</title>
	<author>amaupin</author>
	<datestamp>1268160360000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p><div class="quote"><p>Several others have noted this as well - for Asian languages, Google has a lot of work to do. The Chinese translation near the top is impressive, but while Chinese and Japanese translations are probably pretty good on Google, other Asian languages suffer greatly.</p></div><p>
I have all but given up on Google's Japanese translation.  Altavista (now Yahoo) 's Babel Fish is much more reliable when it comes to Japanese.  Sometimes the Google translation is so wrong that I can't even understand how it came up with the response returned.  At least with Babel Fish I can usually figure out where it missed an idiom or failed to choose the correct meaning of a certain kanji character.
</p></div>
	</htmltext>
<tokenext>Several others have noted this as well - for Asian languages , Google has a lot of work to do .
The Chinese translation near the top is impressive , but while Chinese and Japanese translations are probably pretty good on Google , other Asian languages suffer greatly .
I have all but given up on Google 's Japanese translation .
Altavista ( now Yahoo ) 's Babel Fish is much more reliable when it comes to Japanese .
Sometimes the Google translation is so wrong that I ca n't even understand how it came up with the response returned .
At least with Babel Fish I can usually figure out where it missed an idiom or failed to choose the correct meaning of a certain kanji character .</tokentext>
<sentencetext>Several others have noted this as well - for Asian languages, Google has a lot of work to do.
The Chinese translation near the top is impressive, but while Chinese and Japanese translations are probably pretty good on Google, other Asian languages suffer greatly.
I have all but given up on Google's Japanese translation.
Altavista (now Yahoo) 's Babel Fish is much more reliable when it comes to Japanese.
Sometimes the Google translation is so wrong that I can't even understand how it came up with the response returned.
At least with Babel Fish I can usually figure out where it missed an idiom or failed to choose the correct meaning of a certain kanji character.

	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421682</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424182</id>
	<title>google skynet ?</title>
	<author>Atreide</author>
	<datestamp>1268216160000</datestamp>
	<modclass>Funny</modclass>
	<modscore>2</modscore>
	<htmltext><p>Wasn't Skynet used for translation<br>before it decided for a better future for humanity ?</p></htmltext>
<tokenext>Was n't Skynet used for translationbefore it decided for a better future for humanity ?</tokentext>
<sentencetext>Wasn't Skynet used for translationbefore it decided for a better future for humanity ?</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31538624</id>
	<title>Re:Asian languages and vastly different grammar</title>
	<author>egghat</author>
	<datestamp>1269016500000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Google Translate is 100\% based on statistics, so there are no special algorithms for translating from one language to another. The translation gets better when Google has *a lot* (gogoool) of sentences in a pair of laguage and knows that they have the same meaning. If the language pair is Russian - Ukrainian or German - Swaheli it's almost guaranteed to fail.</p><p>Artficial Intelligent god Peter Norvig (guess where he works) always says: We don't have better algorithms, we just have more data. And if they do not have enough data, well, then Google translates fails.</p><p>There's a very interesting video of a presnataion done by Peter Norvig n YouTube. Highly recommended.<br><a href="http://www.youtube.com/watch?v=HT540VrCDwg" title="youtube.com">Norvig - TODAY: Innovation in Search and Artificial Intelligence</a> [youtube.com]</p></htmltext>
<tokenext>Google Translate is 100 \ % based on statistics , so there are no special algorithms for translating from one language to another .
The translation gets better when Google has * a lot * ( gogoool ) of sentences in a pair of laguage and knows that they have the same meaning .
If the language pair is Russian - Ukrainian or German - Swaheli it 's almost guaranteed to fail.Artficial Intelligent god Peter Norvig ( guess where he works ) always says : We do n't have better algorithms , we just have more data .
And if they do not have enough data , well , then Google translates fails.There 's a very interesting video of a presnataion done by Peter Norvig n YouTube .
Highly recommended.Norvig - TODAY : Innovation in Search and Artificial Intelligence [ youtube.com ]</tokentext>
<sentencetext>Google Translate is 100\% based on statistics, so there are no special algorithms for translating from one language to another.
The translation gets better when Google has *a lot* (gogoool) of sentences in a pair of laguage and knows that they have the same meaning.
If the language pair is Russian - Ukrainian or German - Swaheli it's almost guaranteed to fail.Artficial Intelligent god Peter Norvig (guess where he works) always says: We don't have better algorithms, we just have more data.
And if they do not have enough data, well, then Google translates fails.There's a very interesting video of a presnataion done by Peter Norvig n YouTube.
Highly recommended.Norvig - TODAY: Innovation in Search and Artificial Intelligence [youtube.com]</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422010</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423532</id>
	<title>Youtube?</title>
	<author>Anonymous</author>
	<datestamp>1268163780000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>Now that they turned on automatic sub-titles for many youtube videos, how long until these subtitles can be read in any language?</p><p>And how long until they are synchronized by a synthetic voice in any language?</p></htmltext>
<tokenext>Now that they turned on automatic sub-titles for many youtube videos , how long until these subtitles can be read in any language ? And how long until they are synchronized by a synthetic voice in any language ?</tokentext>
<sentencetext>Now that they turned on automatic sub-titles for many youtube videos, how long until these subtitles can be read in any language?And how long until they are synchronized by a synthetic voice in any language?</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421320</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>Anonymous</author>
	<datestamp>1268140440000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p><div class="quote"><p>Perhaps the data central network it for the net search establishment now is, when attacks together, world large-scale computer.</p></div><p>Is that thing writing a science fiction novel in it's spare time or something?</p><p>I like how it's rooted out Google as the "net search establishment".</p></div>
	</htmltext>
<tokenext>Perhaps the data central network it for the net search establishment now is , when attacks together , world large-scale computer.Is that thing writing a science fiction novel in it 's spare time or something ? I like how it 's rooted out Google as the " net search establishment " .</tokentext>
<sentencetext>Perhaps the data central network it for the net search establishment now is, when attacks together, world large-scale computer.Is that thing writing a science fiction novel in it's spare time or something?I like how it's rooted out Google as the "net search establishment".
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421596</id>
	<title>Good thing /. didn't use the original NYT headline</title>
	<author>Anonymous</author>
	<datestamp>1268142060000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>It was the lovely "Google's Computer Might Betters Translation Tool" (since changed in the HTML title to "Using Computing Might, Google Improves Translation Tool" and "Google&rsquo;s Computing Power Refines Translation Tool" in the online heading):<br><a href="http://languagelog.ldc.upenn.edu/nll/?p=2169" title="upenn.edu" rel="nofollow">http://languagelog.ldc.upenn.edu/nll/?p=2169</a> [upenn.edu]</p><p>There's also some commentary about the article from Ben Zimmer at Language Log...<br><a href="http://languagelog.ldc.upenn.edu/nll/?p=2170" title="upenn.edu" rel="nofollow">http://languagelog.ldc.upenn.edu/nll/?p=2170</a> [upenn.edu]</p></htmltext>
<tokenext>It was the lovely " Google 's Computer Might Betters Translation Tool " ( since changed in the HTML title to " Using Computing Might , Google Improves Translation Tool " and " Google    s Computing Power Refines Translation Tool " in the online heading ) : http : //languagelog.ldc.upenn.edu/nll/ ? p = 2169 [ upenn.edu ] There 's also some commentary about the article from Ben Zimmer at Language Log...http : //languagelog.ldc.upenn.edu/nll/ ? p = 2170 [ upenn.edu ]</tokentext>
<sentencetext>It was the lovely "Google's Computer Might Betters Translation Tool" (since changed in the HTML title to "Using Computing Might, Google Improves Translation Tool" and "Google’s Computing Power Refines Translation Tool" in the online heading):http://languagelog.ldc.upenn.edu/nll/?p=2169 [upenn.edu]There's also some commentary about the article from Ben Zimmer at Language Log...http://languagelog.ldc.upenn.edu/nll/?p=2170 [upenn.edu]</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421246</id>
	<title>Altavista's Babel Fish</title>
	<author>Pojut</author>
	<datestamp>1268139960000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>I remember using Altavista's offering back in the day...the results were shoddy at best.  It could make anything sound like engrish<nobr> <wbr></nobr>:p</p></htmltext>
<tokenext>I remember using Altavista 's offering back in the day...the results were shoddy at best .
It could make anything sound like engrish : p</tokentext>
<sentencetext>I remember using Altavista's offering back in the day...the results were shoddy at best.
It could make anything sound like engrish :p</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424472</id>
	<title>Re:For western languages...</title>
	<author>hughperkins</author>
	<datestamp>1268220960000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>&gt; In short, professionals won't be in danger any time soon.</p><p>Sounds like you're worrying about that though<nobr> <wbr></nobr>;-)</p><p>Technology changes pretty quickly.  Give it twenty years or so.</p><p>I remember when I tried drawing a 3d graph of z = cos ( x * x + y * y ) on my Sinclair ZX Spectrum, in 1982 or so.  Each single pixel took roughly a whole second to plot!</p><p>Now, you can draw such a graph in realtime, 50 frames a second, whilst rotating the whole thing with the mouse. 3D graphics in Doom and then Quake, and now Counter-Strike are increasingly realistic, and run at fluid frame-rates, and simply because the underlying engine - the CPU and GPU - got very very fast.</p></htmltext>
<tokenext>&gt; In short , professionals wo n't be in danger any time soon.Sounds like you 're worrying about that though ; - ) Technology changes pretty quickly .
Give it twenty years or so.I remember when I tried drawing a 3d graph of z = cos ( x * x + y * y ) on my Sinclair ZX Spectrum , in 1982 or so .
Each single pixel took roughly a whole second to plot ! Now , you can draw such a graph in realtime , 50 frames a second , whilst rotating the whole thing with the mouse .
3D graphics in Doom and then Quake , and now Counter-Strike are increasingly realistic , and run at fluid frame-rates , and simply because the underlying engine - the CPU and GPU - got very very fast .</tokentext>
<sentencetext>&gt; In short, professionals won't be in danger any time soon.Sounds like you're worrying about that though ;-)Technology changes pretty quickly.
Give it twenty years or so.I remember when I tried drawing a 3d graph of z = cos ( x * x + y * y ) on my Sinclair ZX Spectrum, in 1982 or so.
Each single pixel took roughly a whole second to plot!Now, you can draw such a graph in realtime, 50 frames a second, whilst rotating the whole thing with the mouse.
3D graphics in Doom and then Quake, and now Counter-Strike are increasingly realistic, and run at fluid frame-rates, and simply because the underlying engine - the CPU and GPU - got very very fast.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423390</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422108</id>
	<title>what is the other side</title>
	<author>Anonymous</author>
	<datestamp>1268146500000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext>A huge surveillance infrastrure that can be used to monitor conversations in real time as they can be converted to text and searched for inference.</htmltext>
<tokenext>A huge surveillance infrastrure that can be used to monitor conversations in real time as they can be converted to text and searched for inference .</tokentext>
<sentencetext>A huge surveillance infrastrure that can be used to monitor conversations in real time as they can be converted to text and searched for inference.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422476</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>GF678</author>
	<datestamp>1268150640000</datestamp>
	<modclass>Informativ</modclass>
	<modscore>2</modscore>
	<htmltext><blockquote><div><p>Going from English to Chinese to English is like taking an English interpretation of what the Chinese are trying to interpret from what someone was saying authentically in English instead of just interpreting into English what someone was authentically saying in Chinese.</p></div></blockquote><p>Exhibit A: <a href="http://winterson.com/2005/06/episode-iii-backstroke-of-west.html" title="winterson.com">http://winterson.com/2005/06/episode-iii-backstroke-of-west.html</a> [winterson.com]</p></div>
	</htmltext>
<tokenext>Going from English to Chinese to English is like taking an English interpretation of what the Chinese are trying to interpret from what someone was saying authentically in English instead of just interpreting into English what someone was authentically saying in Chinese.Exhibit A : http : //winterson.com/2005/06/episode-iii-backstroke-of-west.html [ winterson.com ]</tokentext>
<sentencetext>Going from English to Chinese to English is like taking an English interpretation of what the Chinese are trying to interpret from what someone was saying authentically in English instead of just interpreting into English what someone was authentically saying in Chinese.Exhibit A: http://winterson.com/2005/06/episode-iii-backstroke-of-west.html [winterson.com]
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421684</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31433040</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>kennycoder</author>
	<datestamp>1268227680000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Where do you think "All your base are belong to us" came from?</htmltext>
<tokenext>Where do you think " All your base are belong to us " came from ?</tokentext>
<sentencetext>Where do you think "All your base are belong to us" came from?</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423544</id>
	<title>Forkbomb</title>
	<author>jlintern</author>
	<datestamp>1268164020000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>The translator can't seem to figure out how many times the road has diverged...</p><p> <a href="http://translationparty.com/#6828377" title="translationparty.com" rel="nofollow">two roads diverged in a yellow wood"</a> [translationparty.com] </p></htmltext>
<tokenext>The translator ca n't seem to figure out how many times the road has diverged... two roads diverged in a yellow wood " [ translationparty.com ]</tokentext>
<sentencetext>The translator can't seem to figure out how many times the road has diverged... two roads diverged in a yellow wood" [translationparty.com] </sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31432992</id>
	<title>What I mean is average?</title>
	<author>mestar</author>
	<datestamp>1268227320000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>This one is fun:</p><p>What is the word with most meanings?</p><p>What words have any meaning?<br>What is the meaning of the word?<br>What is the meaning of a word you do?<br>Meaning of words is what to do or what?<br>What is the meaning of words can do something?<br>Mean I can make any kind of words?<br>I can be what the average of the word?<br>Average word what I can?<br>Average words What can I do?<br>Average words I can do?<br>What words do I average?<br>What I mean is average?<br>What is the average that I mean?<br>What is the average of that mean?<br>What do you mean average?<br>I mean what I mean?<br>What do you mean what I mean?<br>I mean what you mean why?<br>What do you mean I mean why?<br>What do you mean mean why?<br>What you mean why?<br>How do you mean why?<br>I mean why is that?<br>What I mean why?<br>How do you mean why?</p><p>It is doubtful that this phrase will ever reach equilibrium.</p></htmltext>
<tokenext>This one is fun : What is the word with most meanings ? What words have any meaning ? What is the meaning of the word ? What is the meaning of a word you do ? Meaning of words is what to do or what ? What is the meaning of words can do something ? Mean I can make any kind of words ? I can be what the average of the word ? Average word what I can ? Average words What can I do ? Average words I can do ? What words do I average ? What I mean is average ? What is the average that I mean ? What is the average of that mean ? What do you mean average ? I mean what I mean ? What do you mean what I mean ? I mean what you mean why ? What do you mean I mean why ? What do you mean mean why ? What you mean why ? How do you mean why ? I mean why is that ? What I mean why ? How do you mean why ? It is doubtful that this phrase will ever reach equilibrium .</tokentext>
<sentencetext>This one is fun:What is the word with most meanings?What words have any meaning?What is the meaning of the word?What is the meaning of a word you do?Meaning of words is what to do or what?What is the meaning of words can do something?Mean I can make any kind of words?I can be what the average of the word?Average word what I can?Average words What can I do?Average words I can do?What words do I average?What I mean is average?What is the average that I mean?What is the average of that mean?What do you mean average?I mean what I mean?What do you mean what I mean?I mean what you mean why?What do you mean I mean why?What do you mean mean why?What you mean why?How do you mean why?I mean why is that?What I mean why?How do you mean why?It is doubtful that this phrase will ever reach equilibrium.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421488</id>
	<title>Their search parsing tech probably helps too</title>
	<author>Phat\_Tony</author>
	<datestamp>1268141460000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>2</modscore>
	<htmltext>Wired recently had <a href="http://www.wired.com/magazine/2010/02/ff\_google\_algorithm" title="wired.com">this article</a> [wired.com] on Google's search algorithm, which mentioned how far ahead it was in parsing language for things like bi-grams to figure out what the meaning of the search was by "figuring out" the relationships between related words in a very human-like way. They have also built an impressive synonym system. These technologies, developed for search, strike me as really critical for good translation.<br> <br>

An exerpt from the article:<p><div class="quote"><p>"People change words in their queries. So someone would say, 'pictures of dogs,' and then they'd say, 'pictures of puppies.' So that told us that maybe 'dogs' and 'puppies' were interchangeable. We also learned that when you boil water, it's hot water. We were relearning semantics from humans, and that was a great advance."

But there were obstacles. Google's synonym system understood that a dog was similar to a puppy and that boiling water was hot. But it also concluded that a hot dog was the same as a boiling puppy.</p></div></div>
	</htmltext>
<tokenext>Wired recently had this article [ wired.com ] on Google 's search algorithm , which mentioned how far ahead it was in parsing language for things like bi-grams to figure out what the meaning of the search was by " figuring out " the relationships between related words in a very human-like way .
They have also built an impressive synonym system .
These technologies , developed for search , strike me as really critical for good translation .
An exerpt from the article : " People change words in their queries .
So someone would say , 'pictures of dogs, ' and then they 'd say , 'pictures of puppies .
' So that told us that maybe 'dogs ' and 'puppies ' were interchangeable .
We also learned that when you boil water , it 's hot water .
We were relearning semantics from humans , and that was a great advance .
" But there were obstacles .
Google 's synonym system understood that a dog was similar to a puppy and that boiling water was hot .
But it also concluded that a hot dog was the same as a boiling puppy .</tokentext>
<sentencetext>Wired recently had this article [wired.com] on Google's search algorithm, which mentioned how far ahead it was in parsing language for things like bi-grams to figure out what the meaning of the search was by "figuring out" the relationships between related words in a very human-like way.
They have also built an impressive synonym system.
These technologies, developed for search, strike me as really critical for good translation.
An exerpt from the article:"People change words in their queries.
So someone would say, 'pictures of dogs,' and then they'd say, 'pictures of puppies.
' So that told us that maybe 'dogs' and 'puppies' were interchangeable.
We also learned that when you boil water, it's hot water.
We were relearning semantics from humans, and that was a great advance.
"

But there were obstacles.
Google's synonym system understood that a dog was similar to a puppy and that boiling water was hot.
But it also concluded that a hot dog was the same as a boiling puppy.
	</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422998</id>
	<title>Re:How different is this from AI research?</title>
	<author>biryokumaru</author>
	<datestamp>1268155680000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>The Chinese Room is stupid, because if I had a mathematical model of the human brain, I could calculate these kinds of ridiculous ideas just as easily as the dude with the book calculates Chinese. The logical extension of the Chinese Room is that no one thinks, which is a pointless conclusion.</htmltext>
<tokenext>The Chinese Room is stupid , because if I had a mathematical model of the human brain , I could calculate these kinds of ridiculous ideas just as easily as the dude with the book calculates Chinese .
The logical extension of the Chinese Room is that no one thinks , which is a pointless conclusion .</tokentext>
<sentencetext>The Chinese Room is stupid, because if I had a mathematical model of the human brain, I could calculate these kinds of ridiculous ideas just as easily as the dude with the book calculates Chinese.
The logical extension of the Chinese Room is that no one thinks, which is a pointless conclusion.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422060</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422088</id>
	<title>From the Menu Example Given...</title>
	<author>Anonymous</author>
	<datestamp>1268146320000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>Google can now track what I order for dinner. I feel so naked.</p></htmltext>
<tokenext>Google can now track what I order for dinner .
I feel so naked .</tokentext>
<sentencetext>Google can now track what I order for dinner.
I feel so naked.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421856</id>
	<title>Re:Why is machine translation so difficult?</title>
	<author>slimjim8094</author>
	<datestamp>1268144520000</datestamp>
	<modclass>Informativ</modclass>
	<modscore>2</modscore>
	<htmltext><p><div class="quote"><p> Is it really that difficult to come up with a set of rules so things are worded correctly?</p></div><p>Yes.</p><p>Longer answer - computers are very bad at context and meaning. Take French to English - it would be one thing if words had the same exact connotations and grammar, and you could just do a find-replace. But, unfortunately, that's not the case. There are many words in French that - depending on context - have many different meanings. In mathematical terms, the mapping of French words to English words is not bijective, nor vice-versa. Take the French word bete - it most literally means "beast", but is often used to mean "stupid". How is a computer supposed to figure out which one to use?</p><p>I just checked and Google Translate actually gets the connotation right, but it's a relatively simple example. Consider the French word "baise" - either kiss or fuck - and a more complicated example. Now... Google gets this right too (creepy!)</p><p>In any case, the only to get perfect translation is to make the computer understand the relevant meanings and connotations of words and stylistic choices... How would you convey a Cockney accent, or Cockney phrasing, in Chinese? In short, you'd need an AI.</p></div>
	</htmltext>
<tokenext>Is it really that difficult to come up with a set of rules so things are worded correctly ? Yes.Longer answer - computers are very bad at context and meaning .
Take French to English - it would be one thing if words had the same exact connotations and grammar , and you could just do a find-replace .
But , unfortunately , that 's not the case .
There are many words in French that - depending on context - have many different meanings .
In mathematical terms , the mapping of French words to English words is not bijective , nor vice-versa .
Take the French word bete - it most literally means " beast " , but is often used to mean " stupid " .
How is a computer supposed to figure out which one to use ? I just checked and Google Translate actually gets the connotation right , but it 's a relatively simple example .
Consider the French word " baise " - either kiss or fuck - and a more complicated example .
Now... Google gets this right too ( creepy !
) In any case , the only to get perfect translation is to make the computer understand the relevant meanings and connotations of words and stylistic choices... How would you convey a Cockney accent , or Cockney phrasing , in Chinese ?
In short , you 'd need an AI .</tokentext>
<sentencetext> Is it really that difficult to come up with a set of rules so things are worded correctly?Yes.Longer answer - computers are very bad at context and meaning.
Take French to English - it would be one thing if words had the same exact connotations and grammar, and you could just do a find-replace.
But, unfortunately, that's not the case.
There are many words in French that - depending on context - have many different meanings.
In mathematical terms, the mapping of French words to English words is not bijective, nor vice-versa.
Take the French word bete - it most literally means "beast", but is often used to mean "stupid".
How is a computer supposed to figure out which one to use?I just checked and Google Translate actually gets the connotation right, but it's a relatively simple example.
Consider the French word "baise" - either kiss or fuck - and a more complicated example.
Now... Google gets this right too (creepy!
)In any case, the only to get perfect translation is to make the computer understand the relevant meanings and connotations of words and stylistic choices... How would you convey a Cockney accent, or Cockney phrasing, in Chinese?
In short, you'd need an AI.
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421216</id>
	<title>Try using google voice transcription</title>
	<author>colin\_faber</author>
	<datestamp>1268139720000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Voice to text attempt 1: "What is. Thank you. Hey Faber what I AM slot. People just want to let you know like Hello Colin, this is already the decision. I think it's going to ask."

Voice to text attempt 2: " Hi.  This  is  the  level  Dell  Computers,  I'm  doing  a  follow,  or  on  the  error  basement  far  start  up  top.  If  that  happens.  I  still  have  the  problem  in  16  Keith  dispatch  number  and  I  gave  you  so  that  into  at  that  back  and  call  us  back  and  we  could  double  shifts  order  with  the  problem.  Thank  you."

The first one was silence that got recorded by accident, the second was from our favorite Indian's over at Dell computer, calling to pester me about how my repairs are going. =)</htmltext>
<tokenext>Voice to text attempt 1 : " What is .
Thank you .
Hey Faber what I AM slot .
People just want to let you know like Hello Colin , this is already the decision .
I think it 's going to ask .
" Voice to text attempt 2 : " Hi .
This is the level Dell Computers , I 'm doing a follow , or on the error basement far start up top .
If that happens .
I still have the problem in 16 Keith dispatch number and I gave you so that into at that back and call us back and we could double shifts order with the problem .
Thank you .
" The first one was silence that got recorded by accident , the second was from our favorite Indian 's over at Dell computer , calling to pester me about how my repairs are going .
= )</tokentext>
<sentencetext>Voice to text attempt 1: "What is.
Thank you.
Hey Faber what I AM slot.
People just want to let you know like Hello Colin, this is already the decision.
I think it's going to ask.
"

Voice to text attempt 2: " Hi.
This  is  the  level  Dell  Computers,  I'm  doing  a  follow,  or  on  the  error  basement  far  start  up  top.
If  that  happens.
I  still  have  the  problem  in  16  Keith  dispatch  number  and  I  gave  you  so  that  into  at  that  back  and  call  us  back  and  we  could  double  shifts  order  with  the  problem.
Thank  you.
"

The first one was silence that got recorded by accident, the second was from our favorite Indian's over at Dell computer, calling to pester me about how my repairs are going.
=)</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421532</id>
	<title>As a foreigner in Japan</title>
	<author>Anonymous</author>
	<datestamp>1268141700000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>I use Google translate frequently, and the translations are not very good, but when you pair it with some basic knowledge of the idiosyncrasies  in the Japanese language. I am at least able to get a basic understanding of the text. But in some cases the results are barely any better than the Babble-fish example above.</p><p>Having some basic understanding of the Language, I can often divide the text into smaller pieces , which seems to improve quality.</p></htmltext>
<tokenext>I use Google translate frequently , and the translations are not very good , but when you pair it with some basic knowledge of the idiosyncrasies in the Japanese language .
I am at least able to get a basic understanding of the text .
But in some cases the results are barely any better than the Babble-fish example above.Having some basic understanding of the Language , I can often divide the text into smaller pieces , which seems to improve quality .</tokentext>
<sentencetext>I use Google translate frequently, and the translations are not very good, but when you pair it with some basic knowledge of the idiosyncrasies  in the Japanese language.
I am at least able to get a basic understanding of the text.
But in some cases the results are barely any better than the Babble-fish example above.Having some basic understanding of the Language, I can often divide the text into smaller pieces , which seems to improve quality.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422600</id>
	<title>Re:Why is machine translation so difficult?</title>
	<author>h4rr4r</author>
	<datestamp>1268151720000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Your sig is wrong,</p><p>MS is doing that too. Nice OS you got there, you might infringe on some of our patents, how bout you pay us so we don't sue you.</p></htmltext>
<tokenext>Your sig is wrong,MS is doing that too .
Nice OS you got there , you might infringe on some of our patents , how bout you pay us so we do n't sue you .</tokentext>
<sentencetext>Your sig is wrong,MS is doing that too.
Nice OS you got there, you might infringe on some of our patents, how bout you pay us so we don't sue you.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421132</id>
	<title>mah piss is frosty</title>
	<author>Anonymous</author>
	<datestamp>1268138940000</datestamp>
	<modclass>Offtopic</modclass>
	<modscore>-1</modscore>
	<htmltext><p>Yup</p></htmltext>
<tokenext>Yup</tokentext>
<sentencetext>Yup</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31425674</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>pszilard</author>
	<datestamp>1268234040000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>I think this benchmark puts the bar a bit too high. First of all, a translator is not designed to produce invertible translations. Moreover, as the goal is to produce an understandable translation of a human-written text, the artifacts introduced by the machine-created translation are most probably magnified quite a bit with the second round of translation.

Still, it's interesting to see that the Google algorithms actually do an OK job even in such an artificial benchmark.</htmltext>
<tokenext>I think this benchmark puts the bar a bit too high .
First of all , a translator is not designed to produce invertible translations .
Moreover , as the goal is to produce an understandable translation of a human-written text , the artifacts introduced by the machine-created translation are most probably magnified quite a bit with the second round of translation .
Still , it 's interesting to see that the Google algorithms actually do an OK job even in such an artificial benchmark .</tokentext>
<sentencetext>I think this benchmark puts the bar a bit too high.
First of all, a translator is not designed to produce invertible translations.
Moreover, as the goal is to produce an understandable translation of a human-written text, the artifacts introduced by the machine-created translation are most probably magnified quite a bit with the second round of translation.
Still, it's interesting to see that the Google algorithms actually do an OK job even in such an artificial benchmark.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423566</id>
	<title>Translation is hard for people.</title>
	<author>Estanislao Martínez</author>
	<datestamp>1268164680000</datestamp>
	<modclass>Informativ</modclass>
	<modscore>3</modscore>
	<htmltext><blockquote><div><p>Why can't software translate as easily as a human? Is it really that difficult to come up with a set of rules so things are worded correctly?</p></div></blockquote><p>But translation isn't easy for humans, so there's no reason to expect it should be easy for computers.
</p><p>Translating from one language to another, for a human translator, basically comes down to this:
</p><ol>
<li>Reading the source text and understanding it as deeply as possible.</li>
<li>Writing an "equivalent" text in the target language.</li>
</ol><p>But the problem is that there is never unique "equivalent" text in the target language, but rather, a lot of alternatives that make different tradeoffs.  This is because a foreign language is part of a foreign culture that has many concepts that are foreign to the source language, and likewise, the source language is part of a source culture that is foreign to the target language.  So translators repeatedly find themselves in situations where either they must leave out something that the source text says or implies, or else say something unnatural in the target language to convey that information.

</p><p>Comparing the grammar of dramatically different languages makes this really clear.  For example, many languages have <a href="http://en.wikipedia.org/wiki/Evidentiality" title="wikipedia.org" rel="nofollow">grammatical evidentiality</a> [wikipedia.org], where statements are subject to grammatical rules that depend on the source of the speaker's information for the statement.  So for example, a language where the equivalent to the sentence "Joe kicked Tom" required the verb to be conjugated differently depending on whether the speaker <i>saw</i> Joe kick Tom or <i>heard</i> so.  If you had to translate an English text to a language like that, you'd have to decide, for each clause in the English text, who is the speaker of the sentence, and whether they know the event first-hand or second-hand, and either of those may often be unclear from the English text.

</p><p>In the converse case, imagine if we're translating from a language like that into English.  Then every sentence in the source language encodes some claim about how the speaker knows the information conveyed in that sentence.  A completely literal translation, in which every English sentence had that information, would be extremely unnatural English writing.  Leaving it out of every single sentence, on the other hand, might leave out something important to understand the text in some cases.  So the translator has to decide in which cases the evidential conjugations of the source language must be translated into a longer English sentence than otherwise necessary.

</p><p>This is one extreme example, but this sort of problem occurs at every level in translation.  Translators often find themselves adding in information that the source text doesn't say, having to use circumlocutions in the target language to express really simple things from the source language, leaving out information from the source text has because it would be too cumbersome to phrase it in the target language, adopting strange conventions in the target language, or having to write supplementary materials to help the readers understand the translation (footnotes, introductions).

</p><p>Or in a few cases, the translators write for people who don't know the source language but are familiar with some of the customs and concepts, or willing to learn them to understand the translation, and then they just leave untranslated words in.  (Examples: lots of philosophy translations from German or French; anime fansubs that leave Japanese honorifics like <i>-san</i> or <i>-sempai</i> in, because the people who use them are anime fans, are at least a bit familiar with them, and actually <i>understand more nuances</i> that way.)

</p><p>So, translation is not a mechanical task, and thus, there can't be a simple set of rules to do it.  It's, as I said at the top, understanding a text in the source language, and writing another in the target language, tailored toward a different audience.  And it requires understanding the audiences of the original text and the translation, and making many informal decisions based on that.</p></div>
	</htmltext>
<tokenext>Why ca n't software translate as easily as a human ?
Is it really that difficult to come up with a set of rules so things are worded correctly ? But translation is n't easy for humans , so there 's no reason to expect it should be easy for computers .
Translating from one language to another , for a human translator , basically comes down to this : Reading the source text and understanding it as deeply as possible .
Writing an " equivalent " text in the target language .
But the problem is that there is never unique " equivalent " text in the target language , but rather , a lot of alternatives that make different tradeoffs .
This is because a foreign language is part of a foreign culture that has many concepts that are foreign to the source language , and likewise , the source language is part of a source culture that is foreign to the target language .
So translators repeatedly find themselves in situations where either they must leave out something that the source text says or implies , or else say something unnatural in the target language to convey that information .
Comparing the grammar of dramatically different languages makes this really clear .
For example , many languages have grammatical evidentiality [ wikipedia.org ] , where statements are subject to grammatical rules that depend on the source of the speaker 's information for the statement .
So for example , a language where the equivalent to the sentence " Joe kicked Tom " required the verb to be conjugated differently depending on whether the speaker saw Joe kick Tom or heard so .
If you had to translate an English text to a language like that , you 'd have to decide , for each clause in the English text , who is the speaker of the sentence , and whether they know the event first-hand or second-hand , and either of those may often be unclear from the English text .
In the converse case , imagine if we 're translating from a language like that into English .
Then every sentence in the source language encodes some claim about how the speaker knows the information conveyed in that sentence .
A completely literal translation , in which every English sentence had that information , would be extremely unnatural English writing .
Leaving it out of every single sentence , on the other hand , might leave out something important to understand the text in some cases .
So the translator has to decide in which cases the evidential conjugations of the source language must be translated into a longer English sentence than otherwise necessary .
This is one extreme example , but this sort of problem occurs at every level in translation .
Translators often find themselves adding in information that the source text does n't say , having to use circumlocutions in the target language to express really simple things from the source language , leaving out information from the source text has because it would be too cumbersome to phrase it in the target language , adopting strange conventions in the target language , or having to write supplementary materials to help the readers understand the translation ( footnotes , introductions ) .
Or in a few cases , the translators write for people who do n't know the source language but are familiar with some of the customs and concepts , or willing to learn them to understand the translation , and then they just leave untranslated words in .
( Examples : lots of philosophy translations from German or French ; anime fansubs that leave Japanese honorifics like -san or -sempai in , because the people who use them are anime fans , are at least a bit familiar with them , and actually understand more nuances that way .
) So , translation is not a mechanical task , and thus , there ca n't be a simple set of rules to do it .
It 's , as I said at the top , understanding a text in the source language , and writing another in the target language , tailored toward a different audience .
And it requires understanding the audiences of the original text and the translation , and making many informal decisions based on that .</tokentext>
<sentencetext>Why can't software translate as easily as a human?
Is it really that difficult to come up with a set of rules so things are worded correctly?But translation isn't easy for humans, so there's no reason to expect it should be easy for computers.
Translating from one language to another, for a human translator, basically comes down to this:

Reading the source text and understanding it as deeply as possible.
Writing an "equivalent" text in the target language.
But the problem is that there is never unique "equivalent" text in the target language, but rather, a lot of alternatives that make different tradeoffs.
This is because a foreign language is part of a foreign culture that has many concepts that are foreign to the source language, and likewise, the source language is part of a source culture that is foreign to the target language.
So translators repeatedly find themselves in situations where either they must leave out something that the source text says or implies, or else say something unnatural in the target language to convey that information.
Comparing the grammar of dramatically different languages makes this really clear.
For example, many languages have grammatical evidentiality [wikipedia.org], where statements are subject to grammatical rules that depend on the source of the speaker's information for the statement.
So for example, a language where the equivalent to the sentence "Joe kicked Tom" required the verb to be conjugated differently depending on whether the speaker saw Joe kick Tom or heard so.
If you had to translate an English text to a language like that, you'd have to decide, for each clause in the English text, who is the speaker of the sentence, and whether they know the event first-hand or second-hand, and either of those may often be unclear from the English text.
In the converse case, imagine if we're translating from a language like that into English.
Then every sentence in the source language encodes some claim about how the speaker knows the information conveyed in that sentence.
A completely literal translation, in which every English sentence had that information, would be extremely unnatural English writing.
Leaving it out of every single sentence, on the other hand, might leave out something important to understand the text in some cases.
So the translator has to decide in which cases the evidential conjugations of the source language must be translated into a longer English sentence than otherwise necessary.
This is one extreme example, but this sort of problem occurs at every level in translation.
Translators often find themselves adding in information that the source text doesn't say, having to use circumlocutions in the target language to express really simple things from the source language, leaving out information from the source text has because it would be too cumbersome to phrase it in the target language, adopting strange conventions in the target language, or having to write supplementary materials to help the readers understand the translation (footnotes, introductions).
Or in a few cases, the translators write for people who don't know the source language but are familiar with some of the customs and concepts, or willing to learn them to understand the translation, and then they just leave untranslated words in.
(Examples: lots of philosophy translations from German or French; anime fansubs that leave Japanese honorifics like -san or -sempai in, because the people who use them are anime fans, are at least a bit familiar with them, and actually understand more nuances that way.
)

So, translation is not a mechanical task, and thus, there can't be a simple set of rules to do it.
It's, as I said at the top, understanding a text in the source language, and writing another in the target language, tailored toward a different audience.
And it requires understanding the audiences of the original text and the translation, and making many informal decisions based on that.
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421986</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>wtbname</author>
	<datestamp>1268145540000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>They just need to do what video card manufacturers do to thwart your little test Mr. Man. Cheat in the translation code to recognize your test, and just regurgitate your original text.</p><p>Then how would you choose the best translation software to buy???? Oh... it's free?</p></htmltext>
<tokenext>They just need to do what video card manufacturers do to thwart your little test Mr. Man. Cheat in the translation code to recognize your test , and just regurgitate your original text.Then how would you choose the best translation software to buy ? ? ? ?
Oh... it 's free ?</tokentext>
<sentencetext>They just need to do what video card manufacturers do to thwart your little test Mr. Man. Cheat in the translation code to recognize your test, and just regurgitate your original text.Then how would you choose the best translation software to buy????
Oh... it's free?</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220</id>
	<title>Similar languages</title>
	<author>Jurily</author>
	<datestamp>1268139720000</datestamp>
	<modclass>Informativ</modclass>
	<modscore>2</modscore>
	<htmltext><p>Sure, you might get something decent if you try to translate from English to German, but what about languages with entirely different thought models behind them, like Chinese or Hungarian? Last time I tried using it, it confused "has been" with "Latvian".</p></htmltext>
<tokenext>Sure , you might get something decent if you try to translate from English to German , but what about languages with entirely different thought models behind them , like Chinese or Hungarian ?
Last time I tried using it , it confused " has been " with " Latvian " .</tokentext>
<sentencetext>Sure, you might get something decent if you try to translate from English to German, but what about languages with entirely different thought models behind them, like Chinese or Hungarian?
Last time I tried using it, it confused "has been" with "Latvian".</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31430686</id>
	<title>Re:Similar languages</title>
	<author>BikeHelmet</author>
	<datestamp>1268214300000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Hey, that's fun!</p><p><a href="http://translationparty.com/#6837832" title="translationparty.com">http://translationparty.com/#6837832</a> [translationparty.com]<br><a href="http://translationparty.com/#6837848" title="translationparty.com">http://translationparty.com/#6837848</a> [translationparty.com]<br><a href="http://translationparty.com/#6837853" title="translationparty.com">http://translationparty.com/#6837853</a> [translationparty.com]<br><a href="http://translationparty.com/#6837858" title="translationparty.com">http://translationparty.com/#6837858</a> [translationparty.com]</p><p>First and last ones are best.<nobr> <wbr></nobr>;)</p></htmltext>
<tokenext>Hey , that 's fun ! http : //translationparty.com/ # 6837832 [ translationparty.com ] http : //translationparty.com/ # 6837848 [ translationparty.com ] http : //translationparty.com/ # 6837853 [ translationparty.com ] http : //translationparty.com/ # 6837858 [ translationparty.com ] First and last ones are best .
; )</tokentext>
<sentencetext>Hey, that's fun!http://translationparty.com/#6837832 [translationparty.com]http://translationparty.com/#6837848 [translationparty.com]http://translationparty.com/#6837853 [translationparty.com]http://translationparty.com/#6837858 [translationparty.com]First and last ones are best.
;)</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421764</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>Anonymous</author>
	<datestamp>1268143620000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>2</modscore>
	<htmltext><p>In Philip K. Dick's obscure 1969 novel <a href="http://en.wikipedia.org/wiki/Galactic\_Pot-Healer" title="wikipedia.org" rel="nofollow">Galactic Pot-Healer</a> [wikipedia.org], the characters play a game based on this very idea.  They take common sayings and figures of speech, and feed them through several language-translation computers.  The results are then sent to a friend, who attempts to figure out what the original phrase was.</p><p>Sometimes when you're reading PKD you get the uncomfortable feeling he really could see into the future.</p></htmltext>
<tokenext>In Philip K. Dick 's obscure 1969 novel Galactic Pot-Healer [ wikipedia.org ] , the characters play a game based on this very idea .
They take common sayings and figures of speech , and feed them through several language-translation computers .
The results are then sent to a friend , who attempts to figure out what the original phrase was.Sometimes when you 're reading PKD you get the uncomfortable feeling he really could see into the future .</tokentext>
<sentencetext>In Philip K. Dick's obscure 1969 novel Galactic Pot-Healer [wikipedia.org], the characters play a game based on this very idea.
They take common sayings and figures of speech, and feed them through several language-translation computers.
The results are then sent to a friend, who attempts to figure out what the original phrase was.Sometimes when you're reading PKD you get the uncomfortable feeling he really could see into the future.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423190</id>
	<title>What does that mean?</title>
	<author>ScrewMaster</author>
	<datestamp>1268157900000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p><div class="quote"><p>in one of the company's few unqualified successes</p></div><p>What does that mean? Google has had more successes in the online world than most of its competitors.</p></div>
	</htmltext>
<tokenext>in one of the company 's few unqualified successesWhat does that mean ?
Google has had more successes in the online world than most of its competitors .</tokentext>
<sentencetext>in one of the company's few unqualified successesWhat does that mean?
Google has had more successes in the online world than most of its competitors.
	</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424502</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>Rocketship Underpant</author>
	<datestamp>1268221380000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>I recently did an evaluation for a translation agency on the state of current machine translation services. Since I translate Japanese to English for a living, that was the pair I was testing.</p><p>Long story short, of the five services I tried that do Japanese-English MT, Google came out the worst. Yes, the worst. Mind you, all of them were terrible. None could produce grammatical English sentences, and most couldn't even translate basic things like Japanese dates properly.</p></htmltext>
<tokenext>I recently did an evaluation for a translation agency on the state of current machine translation services .
Since I translate Japanese to English for a living , that was the pair I was testing.Long story short , of the five services I tried that do Japanese-English MT , Google came out the worst .
Yes , the worst .
Mind you , all of them were terrible .
None could produce grammatical English sentences , and most could n't even translate basic things like Japanese dates properly .</tokentext>
<sentencetext>I recently did an evaluation for a translation agency on the state of current machine translation services.
Since I translate Japanese to English for a living, that was the pair I was testing.Long story short, of the five services I tried that do Japanese-English MT, Google came out the worst.
Yes, the worst.
Mind you, all of them were terrible.
None could produce grammatical English sentences, and most couldn't even translate basic things like Japanese dates properly.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421684</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422316</id>
	<title>Re:Converting that article from English to Chinese</title>
	<author>Ihmhi</author>
	<datestamp>1268149140000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>That's a whole lot better than it was a few years ago.</p><p>They still need to work on their Japanese a good bit, though. Translating my first sentence from English to Japanese to English spit out:</p><p><div class="quote"><p>This is the way it is much more than a few years ago the entire</p></div><p>.</p><p>I believe they are getting very strong on the vocabulary and context clues bit but having a difficult time translating between different Subject-Object-Verb formats.</p></div>
	</htmltext>
<tokenext>That 's a whole lot better than it was a few years ago.They still need to work on their Japanese a good bit , though .
Translating my first sentence from English to Japanese to English spit out : This is the way it is much more than a few years ago the entire.I believe they are getting very strong on the vocabulary and context clues bit but having a difficult time translating between different Subject-Object-Verb formats .</tokentext>
<sentencetext>That's a whole lot better than it was a few years ago.They still need to work on their Japanese a good bit, though.
Translating my first sentence from English to Japanese to English spit out:This is the way it is much more than a few years ago the entire.I believe they are getting very strong on the vocabulary and context clues bit but having a difficult time translating between different Subject-Object-Verb formats.
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422010</id>
	<title>Re:Asian languages and vastly different grammar</title>
	<author>Cyberax</author>
	<datestamp>1268145660000</datestamp>
	<modclass>Informativ</modclass>
	<modscore>2</modscore>
	<htmltext><p>Russian, Polish and Ukrainian translations are laughable as well.</p><p>Even UkrainianRussian translation is mediocre, even though it's pretty trivial (other translators have almost 100\% perfect translations).</p><p>So, good job but still lots to do.</p></htmltext>
<tokenext>Russian , Polish and Ukrainian translations are laughable as well.Even UkrainianRussian translation is mediocre , even though it 's pretty trivial ( other translators have almost 100 \ % perfect translations ) .So , good job but still lots to do .</tokentext>
<sentencetext>Russian, Polish and Ukrainian translations are laughable as well.Even UkrainianRussian translation is mediocre, even though it's pretty trivial (other translators have almost 100\% perfect translations).So, good job but still lots to do.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421682</parent>
</comment>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_23</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424502
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421684
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_7</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421986
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_15</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31438480
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_29</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424618
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_20</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421856
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_10</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423132
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421682
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_4</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423514
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_27</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423304
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_32</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31432766
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421918
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_19</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424278
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421488
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_2</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31538624
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422010
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421682
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_24</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31428086
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421480
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_31</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31425006
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421488
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_14</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423362
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421682
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_30</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31432992
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_21</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421872
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_8</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423058
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_22</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31433040
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_5</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423566
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_13</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424792
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_12</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422476
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421684
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_6</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31426078
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_28</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423544
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_18</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31430634
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_1</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31426530
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422060
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_3</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31430686
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_11</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422998
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422060
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_25</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421320
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_9</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421764
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_26</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31425674
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_17</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422472
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_0</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422316
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_33</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422600
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_10_03_09_2116249_16</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424472
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423390
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421406
</commentlist>
</thread>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.5</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421532
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.3</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421150
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421872
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421764
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421320
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421986
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31430634
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423058
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421684
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422476
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424502
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31425674
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31433040
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422316
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424792
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.8</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421336
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.11</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421406
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423390
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424472
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.9</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421290
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.7</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421918
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31432766
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.6</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421488
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424278
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31425006
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.0</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421220
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421430
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422472
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31432992
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31430686
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31438480
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31426078
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423514
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423544
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31424618
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421682
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422010
---http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31538624
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423362
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423132
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.4</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421732
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.12</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422060
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422998
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31426530
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.10</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421216
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.1</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421704
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423304
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31423566
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31422600
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421856
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation10_03_09_2116249.2</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31421480
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment10_03_09_2116249.31428086
</commentlist>
</conversation>
