Google's Computing Power Refines Translation

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."

Re:Converting that article from English to Chinese

[Daniel Dvorkin]

Yeah, that's actually a pretty good test. Google's version is odd but comprehensible, while Babelfish's is a bunch of ... well ... babble.

Pffft...

[plasticsquirrel]

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.

somebody has to say this

[zlel]

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.

Re:Try using google voice transcription

[amRadioHed]

Yeah, google voice is fun, it's what you get when you combine voicemail and mad-libs.

Re:Converting that article from English to Chinese

[spazdor]

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.

Re:Converting that article from English to Chinese

[RavenousBlack]

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.

Re:Converting that article from English to Chinese

[Jurily]

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.