Copier Auto-Translates Japanese to English

StCredZero writes "Wild. Fuji has created a photocopier that automatically translates documents from Japanese to English. That's pretty nuts. Apparently, the copier can figure out what sections are text, OCR the text, send it to a translation engine, and put the english back into place."

Manga and Anime

[biocute]

Imagine if you upload manga scans to Flickr, and it automatically translates them to English.

Imagine if you upload anime to YouTube, and it automatically includes an English subtitle.

But, the catch is...

[MilesAttacca]

It doesn't seem to be mentioned in TFA, but I have to wonder: Exactly how fast does it copy if it has to translate? I'm sure it's not the near-instantaneous work we've come to expect of our Xeroxes. If the translations aren't just gibberish Engrish, its usefulness will be immense, so the time won't be so much of a concern; but I do still wonder.

Re:I just photocopied this article

[Rocketship Underpant]

That's pretty much what it would be like. Machine translation in general is an extremely difficult problem, and I don't expect to see decent Japanese-English translation software during my lifetime. Nothing less than true artificial intelligence will be required.

Re:I just photocopied this article

[Reality Master 201]

Machine translation has been making great strides in the past few years. You might not see it with sites like babelfish or google translate, but some of the upcoming research systems do quite a good job of accurately translating between langauges. The output might not flow as well as you'd get from a human, but the ideas do get reliably translated between languages. I think it's quite reasonable to think we'll see really usable machine translation software in common use within 10 years.

Now getting the computers to understand what's being communicated beyond stupid keyword recognition - that's a big problem.

Re:I just photocopied this article

[Helios1182]

Either you are old, or a bit naive. I think in the next 10 years we will see significant improvement. It just happens that the general public doesn't have access to the state of the art research. Systems are improving all of the time. They won't, however; reach the level of a fluent human translator for a long time if ever. But for most documents a machine will be able to do a decent job.

Re:Manga and Anime

[Gunslinger47]

Oh, yeah, let me imagine that... given this concrete example. :)

"Sharingan no hontou no chikara ga...kono Uchiha Madara no chikara ga."

Assuming you have a RAW of suitable quality for the machine to accurately read the furigana, the babelfish-esque translation for this would be:

"True power of copying wheel eye... among these the power of variegation."

Yeah... Anyway, there are literally pages of discussion on Wikipedia regarding this line because some human beings accidentally mistranslated this for the speed scanlations. For the record, the best translation I've seen is:

"The Sharingan's true power. My, Uchiha Madara's power."

Referring to himself in third-person sounds much less awkward in the original Japanese.

It's the voluntary collaboration with a data tap..

[cheros]

What is wild is that anyone with half a working braincell would use a photocopier in an office where a copy of every document is sent to an uncontrolled 3rd party for translation.

Yeah, put that baby in the CEO's office..

(not the mention the fact that there's a huge gap between mechanical translations and the subtleties of language only a skilled translator and/or native speaker has any hope of translating).

So, IMHO cute idea, but don't expect me to bu one any time soon.

Re:All the cartoon drawings...

[The Spoonman]

Or..."all your base are belong to us. Make your plan."

This copier thing sucks, though. It eliminates my ability to use an analogy that's near and dear to my heart. When I build a server, I use a base image. I've had many, many people tell me stupid things like "Oh, I don't use images. Sometimes when you use images, things get all out of sync and they're not consistent." Uh, yeah they are, idiot. That's the whole point of using an image. When I build a new server, the only thing that differs between it and the master image is the name and IP address. My statement to them is "Saying machines come out inconsistent when you use images is like saying I took a document with words on it in English, put it on the copier, made ten copies and three of them came out in French." Now that we can actually do that (or will when they put an English-French translation module into my copier) what am I going to tell these twits!?

Re:Great!

[IngramJames]

Actually, an interesting point from what I wrote above: I spent about 2 months (on and off) trying to work out what the Tokyo office wanted. Many emails, and quite a few phone calls were made. Then we sent out a guy to finish off the code (he'd started it in London, based on what we THOUGHT was required). He had my research and English spec (and his preliminary code) as the basis of what was going to be done, but basically, *he* sorted the final stuff out on the spot, in less than a week. It turned out that a lot of the stuff I thought was wrong, or not *quite* right.

It emerged (and I *never* thought I'd say this, let alone write it) that having a coder on the spot, saying "if we use these rules, you'll get THIS result" turned out to be *more* efficient than getting the spec right beforehand. More accurate, as well.

I simply could *not* nail down an accurate spec for 2 months, because of the problems of translation. The Tokyo guys didn't speak perfect English. I speak no Japanese. We were all intelligent business people; I'm a geek, and a Japanese guy was a geek. We couldn't do it. The only language which worked, at the end of the day, was the logical programming language which spat out results, and the analysis thereof.

When we got to THAT level, the business people could finally say: "change this to Y", or "this value should be X". They had the Japanese technical spec, the system output, and the business knowledge. Only then could we resolve *every* issue.