10289840
story
Comments: 142 + - Technology: Google's Computing Power Refines Translation on Tuesday March 09, @07:48PM
background: url(//a.fsdn.com/sd/topics/topicgoogle.gif); width:104px; height:38px;
google
background: url(//a.fsdn.com/sd/topics/topictech2.gif); width:60px; height:80px;
technology
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."
Related Stories
I like work; it fascinates me; I can sit and look at it for hours.
All trademarks and copyrights on this page are owned by their respective owners. Comments are owned by the Poster. The Rest © 1997-2010 Geeknet, Inc.
Converting that article from English to Chinese to (Score:5, Interesting)
English, with Google Translate:
--- ... 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.
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.
---
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
---
Re:Converting that article from English to Chinese (Score:5, Insightful)
Yeah, that's actually a pretty good test. Google's version is odd but comprehensible, while Babelfish's is a bunch of ... well ... babble.
Parent
Re: (Score:3, Interesting)
Re:Converting that article from English to Chinese (Score:4, Insightful)
This doesn't actually mean the translation is any better: all it means is that the Chinese generated by Babelfish is more easily translated back to english, perhaps because it makes even less sense in Chinese. A translation function could be conceived which is a strict, reversible bijection, so that playing this translation game would give you your original English back, word-for-word. Doesn't guarantee that the intermediate Chinese step is in any way comprehensible.
Parent
Re:Converting that article from English to Chinese (Score:4, Insightful)
A translation function could be conceived which is a strict, reversible bijection, so that playing this translation game would give you your original English back, word-for-word.
That's the main problem with translations: they're not strict, and sometimes not even reversible. In every language there are common phrases which make perfect sense to someone thinking in the language, but are untranslatable to the point where you as a translator just rephrase the whole sentence (example: "is right up Google's alley"). Then, if you get another translator to translate it back to the original language, you sure as hell won't get the original phrase back (assuming both translations are perfect in terms of understandability and conveying the message).
Then you have words that don't exist in the target language, like "brute-force" or "computing horsepower", or even concepts that don't exist.
I think the fact that we can understand machine translations is more a tribute to the error correction mechanisms in our brain than anything else.
Parent
Re: (Score:2)
..In every language there are common phrases which make perfect sense to someone thinking in the language, but are untranslatable to the point where you as a translator just rephrase the whole sentence (example: "is right up Google's alley"). Then, if you get another translator to translate it back to the original language, you sure as hell won't get the original phrase back (assuming both translations are perfect in terms of understandability and conveying the message).
Then you have words that don't exist in the target language, like "brute-force" or "computing horsepower", or even concepts that don't exist.
I think the fact that we can understand machine translations is more a tribute to the error correction mechanisms in our brain than anything else.
Awl hour translate spume waffle. Ewe no other gender knot exchangeable!
Re: (Score:3, Interesting)
Plus, round-trip translation at least doubles the error compared to an actual application which would involve one-way translation (and probably more, since the "return-trip" translation is starting with a poor quality input). A much more fair test would be compar
Re:Converting that article from English to Chinese (Score:5, Interesting)
Der Spiegel offers version of some of its stories in English. They aren't direct translations, but quite similar.
Here's part of a story published in english [spiegel.de]:
And the same story, published in German, [spiegel.de] translated to English by google:
And babelfish translation of the same story:
I do think the google version is significantly better.
Parent
Re: (Score:2)
I don't think so. Things get lost in translation with humans already. There are phrases I simply can't translate in languages I'm fluent in, idioms and the like. And when humans pass along information, it also gets distorted, simplified, and the like - language is a vague, flexible thing. So we're trying to give the machine a test impossible to pass, a Turing test where most of us don't even have any real experience how well a human would do it as a frame of refe
Re:Converting that article from English to Chinese (Score:4, Insightful)
Parent
Re: (Score:3, Informative)
Exhibit A: http://winterson.com/2005/06/episode-iii-backstroke-of-west.html [winterson.com]
Re: (Score:2, Interesting)
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.
Re: (Score:2)
Re: (Score:2)
Soon the super karate monkey death car would park in my space... but Jimmy has fancy plans, and pants to match!
Feel my scales donkey donkey donkey donkey donkey.
Also...
I stole a car! I mean, a sycamore tree...
Re: (Score:2)
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.
Not from NY Times (Score:3, Informative)
Last week's The Economist adressed this issue (http://www.economist.com/specialreports/displaystory.cfm?story_id=15557431). NY Times recycled it
Similar languages (Score:3, Informative)
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".
Re:Similar languages (Score:5, Funny)
I've worked on payment processing for web sites in Korea before. The translations of error messages we get from the system, then passed through Google translate, are exactly as good as the translations we get back from a human translator. That is, not useful at all.
Parent
Re: (Score:2)
And what about countries where people actually speak English [google.com]?
Re: (Score:2)
Are you sure the human translators aren't just using google translate?
Re: (Score:3, Interesting)
Are you sure that the error messages are even meaningful in Korean?
Re: (Score:2)
No, I'm quite sure they aren't.
Re: (Score:3, Funny)
Its strange, when translated from Korean, all they say is Whoosh!
Re:Similar languages (Score:5, Interesting)
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.
Parent
Re: (Score:3, Interesting)
That is fun. Your sig breaks it [translationparty.com].
Re: (Score:2)
Not quite what I meant by "broke it". The phrase just changed back and forth between two different translations before the script gave up.
Re: (Score:2)
It doesn't work with my setup of IE or Chrome, the only two browsers I'm fiddling with these days. It must want you to totally drop your pants on security settings or something.
Asian languages and vastly different grammar (Score:5, Interesting)
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.
Parent
Re: (Score:3, Informative)
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.
Re: (Score:2)
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.
Altavista's Babel Fish (Score:2)
I remember using Altavista's offering back in the day...the results were shoddy at best. It could make anything sound like engrish :p
Pffft... (Score:3, Insightful)
somebody has to say this (Score:2, Insightful)
For western languages... (Score:3, Interesting)
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.
I noticed that they were using my web site (Score:2, Interesting)
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 (leadi
Their search parsing tech probably helps too (Score:3, Interesting)
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.
Re:Their search parsing tech probably helps too (Score:5, Funny)
But it also concluded that a hot dog was the same as a boiling puppy.
There is nothing wrong with that. My son forms connections like that all the time, and he is only slightly younger than google.
Parent
Why is machine translation so difficult? (Score:2)
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?
Re: (Score:3, Informative)
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 ofte
Re: (Score:2)
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.
Re: (Score:2)
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
Translation is hard for people. (Score:3, Informative)
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:
But the problem is that there is never unique "equ
Pretty good and impressive as it translated (Score:2)
What does that mean? (Score:2)
in one of the company's few unqualified successes
What does that mean? Google has had more successes in the online world than most of its competitors.
Low-volume languages? (Score:2)
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 vol
google skynet ? (Score:3, Funny)
Wasn't Skynet used for translation
before it decided for a better future for humanity ?
Re: (Score:3, Insightful)
Yeah, google voice is fun, it's what you get when you combine voicemail and mad-libs.
Re: (Score:2)
I guess it depends on the language a lot.
I've found that japanese translations are often awkward, and you have to 'force' a correct translation by changing context, structure, etc.
Alternatively, the french translation is very, very good, picking up subtleties of formal / informal speech, slang and abbreviations.
Re: (Score:2)
Google's french translations are very strong:
- Give us our daily bread (unsure what the catch is w/ this phrase, but)
- Donnez-nous notre pain quotidien
- Sharks are predatory carnivores
- Les requins sont des carnivores prédateurs
- The loanshark wants his bread
- L'usurier veut son pain
All translated with the correct context
Re: (Score:2)