Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
×
Printer Hardware

Copier Auto-Translates Japanese to English 244

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."
This discussion has been archived. No new comments can be posted.

Copier Auto-Translates Japanese to English

Comments Filter:
  • by Anonymous Coward
    Turn into actual pictures of people, too! Amazing!
    • Tattoos.. (Score:2, Funny)

      by Cuznmark1 ( 1163359 )
      This may help people from making some big mistakes with their tats...
    • by rde ( 17364 ) on Friday September 28, 2007 @04:34AM (#20779903)
      Ooh, I hope not. If it does, then it means that it's got a real prediliction towards anime. That could produce some interesting translations, such as...

      Dear Sir,
      Your opponent is me! With regard to your memo dated 14th inst., I'll never forgive you, vampire bastard! Super ultra science business meeting, engage!
      Noooooooooooooooo!

      Yours faithfully,
      Bob Morton
      Chief Gundam Officer
      • Re: (Score:3, Insightful)

        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 betwe
  • Not new (Score:5, Funny)

    by Anonymous Coward on Thursday September 27, 2007 @10:02PM (#20777977)
    They've been using this for years to translate instruction manuals.
    • Re:Not new (Score:5, Funny)

      by nmb3000 ( 741169 ) on Thursday September 27, 2007 @11:04PM (#20778381) Journal
      They've been using this for years to translate instruction manuals.

      You're not joking [worsethanfailure.com]. It is completely worth your time to read this entire image.
      • What the hell do you do with an 'ether lord fucking net'?
      • Re: (Score:3, Funny)

        by c3ph45 ( 911279 )
        Written by Miss Teen South Carolina.
      • Well, I mean the packing list includes a "for glue the sex rubber mat" -- so it can't possibly be that bad, could it?

        Actually, ew. It's an ethernet switch. I really don't want to know what that bit's for!
        • Well, I mean the packing list includes a "for glue the sex rubber mat" -- so it can't possibly be that bad, could it? Actually, ew. It's an ethernet switch. I really don't want to know what that bit's for!

          It sounds like they've come up with the greatest invention of all time - an ethernet switch that allows you to completely circumvent the computer and have your pr0n delivered directly to the ultimate....ah...consumer. God bless those crazy bastards.

      • by Flying pig ( 925874 ) on Friday September 28, 2007 @05:34AM (#20780139)
        Years ago I read a German press release about the then-new Intel 486. There was a completely confused reference to it having an attached buoy for a small boat (I am not joking). It took me about ten minutes to realise that the author had no idea at all of how to translate "integrated floating point unit", and presumably had come somewhere across the word "boot".

        Obviously the translator was all at sea.

    • Re:Not new (Score:5, Funny)

      by flyingfsck ( 986395 ) on Thursday September 27, 2007 @11:23PM (#20778463)
      Japanese instruction is to be helping and not to be laughful at.
  • Manga and Anime (Score:3, Insightful)

    by biocute ( 936687 ) on Thursday September 27, 2007 @10:11PM (#20777981)
    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.
    • Re: (Score:3, Interesting)

      by Kandenshi ( 832555 )
      Automatic english subtitles for an anime? That's more of a job for speech recognition software(which is also being worked on, one of the profs in my department had a friend working on Japanese to English speech recognition/translation many years ago).

      This OCR based stuff would still be handy for automatically translating manga I suppose though.
      I know that there are a few things out there in Japanese that haven't been released in English yet I wouldn't mind.
      • Re: (Score:3, Interesting)

        by liquidsin ( 398151 )
        ok, so imagine if your dvd player could translate the japanese subtitles to english...
    • Re:Manga and Anime (Score:5, Informative)

      by dancingmad ( 128588 ) on Thursday September 27, 2007 @10:51PM (#20778297)
      Imagine if you upload anime to YouTube, and it automatically includes an English subtitle.

      Without the kanji, since a large number of Japanese words are homophones, I can't see this being practical in the near future. Text is different - with the kanji, it's not terribly difficult to look up the correct word and with kana grammar beside it, the task gets much easier. I can't see a machine understand a conversation in context, however.
    • Re: (Score:2, Insightful)

      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 f

    • by glwtta ( 532858 )
      Imagine if you upload manga scans to Flickr, and it automatically translates them to English.

      Truly, on that day my life would be complete!
    • Imagine if you upload manga scans to Flickr, and it automatically translates them to English.

      I guess it's just a matter of time before Viz and other manga translators try to have this thing declared illegal. We can't have people importing their own manga from Japan, now can we ? After all, then Viz couldn't take years to translate it.

      I wonder how they're going to go about it. Maybe language barrier could be considered effective copy protection ? It's not that different from crypting schemes like the C

    • Imagine if you upload Monty Python episodes to the photocopier and you get a Japanese guy in the tobacco shop asking about hovercrafts full of sushi.
    • Imagine there was a program that could talk to you just like it was another human being, and you couldn't tell that it was a computer.

      Hey as long as we're imagining shit that doesn't exist and doesn't look like it's going to happen any time in the near future...
  • by Spy Hunter ( 317220 ) on Thursday September 27, 2007 @10:13PM (#20777991) Journal
    StCredZero "writes wildness. Fuji drew up the photocopying machine which automatically translates the document from English from Japanese. That is the clean nut. With respect to appearance, as for the copier the text, as for OCR what kind of section text, to send that to the translation engine, and in the place English". You reset, or can grasp.
    • Re: (Score:3, Insightful)

      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: (Score:2, Interesting)

        Thanks to that, people like me (translators, though I'm still in the making) will still find a job in the foreseeable future :D
      • Re: (Score:3, Insightful)

        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 co
      • by Helios1182 ( 629010 ) on Thursday September 27, 2007 @10:29PM (#20778127)
        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.
        • by arth1 ( 260657 )

          Either you are old, or a bit naive. I think in the next 10 years we will see significant improvement.

          Going from 20% accuracy to 40% accuracy is a "significant improvement" -- it's a 100% improvement. And a 25% reduction of crap, if you want to look at it the other way.
          That still doesn't mean it's going to be usable.

          As long as you're on the bad side of 99% accuracy, it's nowhere near "good enough". 99% accuracy still means there's going to be a couple on errors on every single page. Some of the errors mig

        • by Valdrax ( 32670 ) on Friday September 28, 2007 @12:54AM (#20778989)
          Either you are old, or a bit naive. I think in the next 10 years we will see significant improvement.

          Yeah, 'cause researchers have long promised us that AI will reach us in 10 years. <sarcasm>

          Seriously, I think you underestimate the difficulty of translating. Have you done any major foreign-language translation -- especially of conversational speech? My experience has primarily been with Japanese and English, and I'll tell you right now that it can be nightmarish.

          Sentence fragments are the worst part. Japanese has a completely different word order from English. All modifiers (including phrases and clauses) come before the word they modify, and the language has a Subject-Object-Verb order. "I just saw the man who stole my friend's watch last Tuesday" becomes "Just I Last Tuesday friend's watch stole man saw." Now try translating that from Japanese to English when the sentence is cut in half.

          Worse, the language has very different levels of allowed vagueness. "Complete" sentences in Japanese can contain just a descriptor or an action without any specification of who did/was what. Conversely, translating "3 of them" in English to Japanese is hard because you have to know "3 of what?" to know what counting suffix to use.

          Another problem is that many very different words sound exactly the same when conjugated to the gerund or perfective forms. English has a number of homonyms, but there are MANY more opportunities for mix-ups if you don't have access to kanji to tell the semantic meaning apart because Japanese has a much more limited range of phonemes. For example, take "katte" which is the gerund form of the verbs "kau" (buy), "kau" (keep/raise), "karu" (cut), "karu" (spur on), and "katsu" (win). That's 5 completely different verbs that conjugate to the same sound. If they're written phonetically or your going from speech, then you have to be able to understand the meaning behind the words to translate. (Did I mention earlier that you may not have an explicit subject and object to go off of?)

          Then you get into issues of translating things like politeness levels, different ways of addressing people, and other concepts that don't translate well into English or concepts like singular vs. plural that are dropped in going to Japanese. Let's not even consider puns and poetry!

          These are not trivial issues. An automatic translator would need to somehow be able to conceptualize what a person is trying to speak about, which would require understanding the story being told and an ability to predict where they are going with it. This will require strong AI.

          Accurate and intelligible translation is an art -- not a science -- because it requires an intuitive and empathetic ability to understand the mind of the speaker well enough to map their thoughts into a different method of expression.
          • You're thinking of translation in terms of human methodologies- learn the language-specific grammar and vocabulary of individual words- rather than as a mapping problem: map a sentence (which is often the smallest unit of language you care about) in one language into a sentence in another language. Machine learning applications have already made significant progress in this area, and with growing data sets and refinements in the algorithms, their ability to statistically "predict" what a sentence in one la
            • Re: (Score:2, Interesting)

              by Anonymous Coward
              The problem with this is that languages such as Japanese have a tendency to suppress information that is obvious (to a human) from context. So there are many single sentences that are literally untranslatable out of context.

              You may well have an amazing statistical technique that can compare your web page sentence-by-sentence to a massive corpus of bilingual pages, but how is it going to know whether "kondo ha simasu" on your page means "this time I'll do it", "this time you'll do it", "next time they'll do
            • Re: (Score:3, Interesting)

              by mstahl ( 701501 )

              What the grandparent post is saying is that you might not have a full sentence, nor might a full sentence even provide sufficient information to perform the translation accurately. If Japanese and English were so easy to translate back and forth, don't you think that humans [engrish.com] would have an easier time of it?

              The method of analyzing bilingual pages is great for languages that have a similar structure to one another, like italian and spanish. In fact, this is part of how I learned spanish, by reading a bilingua

              • Re: (Score:2, Interesting)

                by l0cust ( 992700 )

                What the grandparent post is saying is that you might not have a full sentence, nor might a full sentence even provide sufficient information to perform the translation accurately.

                I think you are missing the point a bit. A native Japanese speaker will not have any problem understanding the japanese sentence even with the insufficient context(from the perspective of say an Englishman) but he will have problem with a sentence of similar sort which is in English even if he understands english quite well. The l

              • These guys saying that the technology won't be here within their lifetime have to be ancient or just forgetting how rapidly the pace at which technology accelerates has been increasing of late. How long ago was it that this here "Internet" only had a few hundred nodes?

                I am not exaggerating when I say that automatic translation from extremely dissimilar languages requires strong AI. You need to be able to guess what a person is thinking from what they're expressing to map it into a different way of expressi
          • Seriously, I think you underestimate the difficulty of translating. Have you done any major foreign-language translation -- especially of conversational speech?

            I totally agree with your excellent post. I know Russian very well and in the past I have used what is considered to be the best EnglishRussian translation program. It was certainly better than nothing, but it had many flaws. Many European languages, including Russian, use double negatives. For example, it is quite to correct to say in Russian
        • by ross.w ( 87751 )
          Problem is, a lot of the time the human translators [engrish.com] aren't much better (although they too are improving)
      • Re: (Score:2, Interesting)

        by AaxelB ( 1034884 )
        Incidentally, I just went to a talk today by Jeff Dean (a Google fellow) in which he mentioned Google Translate, and some of the things they're doing to develop a viable machine translation system. One of the things that stuck with me was maintaining a database of statistically probable 5-word phrases in the target language, obtained largely by analyzing un-translated news stories and other such things. Also, to the extent that examples are available, they'll directly compare documents that were translated
    • What you say???
  • by alshithead ( 981606 ) on Thursday September 27, 2007 @10:14PM (#20777995)
    It translates to Engrish?
  • 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.
  • You have no chance to survive make your time. :)
  • Engrish (Score:3, Interesting)

    by Nasarius ( 593729 ) on Thursday September 27, 2007 @10:15PM (#20778017)
    Between the inaccuracy of unproofed OCR and the poor quality of machine translation, I can't imagine that the results are very good.
  • I think of that this is rather sweet. As for converting Japanese rather than easy, converting other manner with a certain manner, with other manner hard. As for existence of Chinese character, for example, thing is made easier. But (with easily from Chinese character. Chinese which becomes complete)

    -:sigma.SB

  • by Anonymous Coward on Thursday September 27, 2007 @10:23PM (#20778081)
    [Reading from his book, "Jimmy James: Macho Business Donkey Wrestler," translated to Japanese and back again]
    Jimmy: I had a small house of brokerage on Wall Street. Many days no business comes to my hut. 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...
    [pauses while turning page]
    Jimmy: dung.
  • Finally! Now I can pour my collection of Hentai into one and enjoy the interesting story lines and character development...

    But I wonder does the english language contain enough exclamations though: Uh!, Ah! ?

  • It's impossible... (Score:5, Informative)

    by wanderingknight ( 1103573 ) on Thursday September 27, 2007 @10:28PM (#20778117)
    ...for a machine, under the current paradigms (that is, no true artificial intelligence) to properly translate something. Translation is not an exact science, and you can't expect to get a decent translation by just having a word-per-word approach. Heck, not even a sentence-per-sentence or paragraph-per-paragraph approach would ever be enough. Translation requires deep social knowledge--you need to know what you are translating, from whom you are translating, for whom you are translating... that is, you need to enclose your translation in a sociological context. No machine can ever wish to do that without artificial intelligence. It's hard enough as it is to get a human being to understand that word-per-word translation is stupid--imagine telling that to your CPU core.

    Disclaimer: I'm a translation student myself ;)
    • by kklein ( 900361 ) on Thursday September 27, 2007 @10:59PM (#20778345)

      Disclaimer: I'm a second language acquisition researcher and assessor.

      I concur. Absolutely. Language is not pure information; it's information shorthand. It assumes a high degree of already-shared knowledge about the world. Some of these assumptions are near-universal; many are not.

      Japanese and English (my languages) offer a great example, especially as it pertains to machine translation. Whereas English is a subject-predicate language, where basically all the information is encoded in the language stream, Japanese is a topic-comment language, where, once set, the "subject" is not re-stated until it changes. Beginning Anglophone learners of Japanese make the mistake of putting a "wa" to denote what they think of as the subject in every sentence, when it does not need to be there. "Wa" is a topic marker; not a subject marker.

      This is a fundamentally different way of thinking about language and, therefore, about the world. Germanic languages seek to operate regardless of context; Asian languages seek to augment (or "comment on") it. If you've ever felt that Japanese people who speak English are beating around the bush or being vague, part of that is cultural, but part of that is the language of the culture that does not require explicitness. A big part of learning Japanese or, for Japanese people, of learning English is learning how to think about the world and about human interactions in a very different way.

      Machines aren't human. They are information processors. They don't know what a "cat" is; they just know that it's a piece of code that can be slotted into a certain place in a set of syntax. Until machines are really intelligent (and I don't think that will be anytime soon), expect more crappy translation than useful. Anyone who tells you otherwise is probably selling something (a crappy machine translator, to be exact!).

      • Re: (Score:2, Interesting)

        Yeah, that's true. My native tongue is Spanish, I'm studying English translation, and I have a decent knowledge of Japanese (my idea is to also study Japanese translation in the future). I've also studied (though not without a certain degree of displeasure) French and Latin. Out of those five languages, Japanese is my favorite one, mainly due to the musicality of its sounding. And yeah, it's highly contextual--so highly that many sentences in a common Japanese dialog would sound outright stupid without a pr
      • by Valdrax ( 32670 )
        Japanese and English (my languages) offer a great example, especially as it pertains to machine translation. Whereas English is a subject-predicate language, where basically all the information is encoded in the language stream, Japanese is a topic-comment language, where, once set, the "subject" is not re-stated until it changes. Beginning Anglophone learners of Japanese make the mistake of putting a "wa" to denote what they think of as the subject in every sentence, when it does not need to be there. "Wa"
      • by arth1 ( 260657 )

        If you've ever felt that Japanese people who speak English are beating around the bush

        I think you mean "Sensation is to be had for Japan people between English languages, fights of the hibiscus round will be".

        HTH, HAND,
        --
        *Art
      • Re: (Score:2, Funny)

        by Monchanger ( 637670 )

        Anyone who tells you otherwise is probably selling something (a crappy machine translator, to be exact!).

        Well put, and you may get free shipping if you add a "USB Humping Dog" to your cart:

        Or get your hump on with a USB Humping Dog -- on sale now, satisfaction guaranteed! http://www.digitalworldtokyo.com/index.php/shop/product/usb_humping_dog/ [digitalworldtokyo.com]

        "Satisfaction guaranteed"? For the buyer or the dog?

        (so glad I RTFA)

    • by Mike89 ( 1006497 )
      Machines can't even translate back and forward properly. For example, Google Translator.

      My girlfriends in Germany so one of my friends was messing around translating silly things to German. For one of them, he put:
      Selina's tang is mighty fine
      Which translated to:
      Der tang von Selina ist mächtige Geldstrafe

      When I translated this back to English (he didn't tell me the original phrase till later:
      The seaweed of Selina is powerful fine ... Seaweed? Odd!
      • by Splab ( 574204 )
        I get Seaweed as explanation for 'tang' when I look it up in dict (webster), it seems to me the machine actually hit your phrase quite right both ways. Deutsch is notoriously hard to translate because they got a messed up sentence construction - so the fact that the machine got it right both ways is pretty amazing to me.

        Now the tang meaning you had was obviously something else, but from one sentence it's impossible for a machine or in fact a human to figure out which it is. (Since I haven't seen the word "t
        • Oh, German sentence structure is simple compared to many languages. It is a SVO language in general, it's only a certain class of sentences that have the verb-at-end oddity. It's no more odd than us Norwegians occasionally putting the verb first. ("Du sier det. Sier du det?")
  • "Wildness. Fuji drew up the photocopying machine which automatically translates the document from English from Japanese. That is the clean nut. With respect to appearance, as for the copier the text, as for OCR what kind of section text, to send that to the translation engine, and in the place English". You reset, or can grasp
  • If you sit on the glass and photocopy your ass, it just switches to "Enlarge by 50%" mode.
  • Instead of the next guy complaining he's getting duplex and stapling, you'll have him pulling the box apart to figure out why it's in a foreign language. Helpdesk fun for all.
  • by el_flynn ( 1279 ) on Thursday September 27, 2007 @11:45PM (#20778623) Homepage
    ...before we see photos of the scanned documents in http://www.engrish.com/ [engrish.com] ... What were they thinking of??
  • Pretty soon, you'll be hearing this at the office: "Damn copier! First, I got a paper jam. I finally got that fixed - but my hands are all covered in toner. Now, all my documents are coming out in a different language! What's going on? I can't even tell what language this is! Grrrrrr"
  • Is it standalone, or does it phone home? If it sends the content out for translation, it's a huge security hole for an organization.

  • This is vely intelesting! Vely!

    Doshte nobody invented befole, I don't know! Cullently I'm using baka velsion online; it wolks pelfectly!
  • Common exercise: take the article, drop its text into Babelfish [altavista.com], translate it from English to and back again. When doing so from English to Japanese and back, the results are:

    The translator of the specialist may face when being the technology which in the job placement place which crosses the world Fuji Xerox developed because of the most recent prototype photocopy machine it makes well, directly. The Japanese show [ the device of subscription link ] only presently, while maintaining the layout of the or

  • My street is taken over by Latino gangs. (Most of the gang members are kids from Central America.) These guys hang out in front of my building selling rock all day.

    The owner's had cameras installed to deter the selling of crack in front of the building. The problem is, nobody cared. The cameras are small and not easily seen. They went about slingin' rock as usual.

    I decided to print up a sign with a big camera on it. I typed out something like "This building is watched by Surveillance Cameras. Any illegal ac
    • "This building is watched by Surveillance Cameras. Any illegal activity will be recorded and taken to the police."

      Este edificio se encuentra vigilado por Cámaras de Monitoreo. Toda actividad ilegal será grabada y entregada a la policía.

      There are of course many other ways to put it, but if they laugh this time will be because they don't give a hoot about the cameras or the police. I hope your problem gets solved!

    • Biblefish translations to spanish says something like This building _is being looked at_ by Surveillance Cameras (lit.) Any illegal activity will be registered and taken _the_ police. So, you actually register the activities, but take the police away, not the activities to the police.

      Better is the portuguese translation: This building is taked attention by Surveillance Cameras. All illegal activity (that is allright for brasilian portuguese) will be recorded and the police will be examined.

      Italian and ge
  • As an research chemist for a large company, I have had to teach myself the unique language of machine translated Japanese for when I'm in literature search mode. We pay $30 a pop for an instantaneous machine translated JP patent through a web-based service. The service is tuned to patent phrases so not as bad as Engrish, but it takes getting used to. The translations are good enough to get the gist, but if the reference is going to be used as prior art for a patent filing, we'll spring for a human translati
  • Fuji Xerox's secret lies in networking the unnamed copier to a dedicated translation server and combining this with algorithms that can distinguish between text, drawings and lines for maintaining page layouts.

    In other words, it's not a translation box at all. It's a networked scanner/copier that passes the scan to a server parked somewhere else to modify the page and send it back to the printer.

    To call it a translator without mentioning the big box sitting across the office that goes with it, is a bit fra
  • This is no more amazing than taking your desktop OCR software, scanning a page, pasting the result into Google Translate, and printing the resulting page. The reason nobody is shipping this is because the translation isn't good enough yet to make it worthwhile.
  • I've played around with a lot of OCR technology and I have to say, it just doesn't work perfectly yet. Anyone looking to just get text recognized, they'd better be prepared to run it through a word processor and give it an additional proofreading. And we also know how effective babelfish is. So we're to expect that they can take raw text freshly OCR'd, run it through a babelfish workalike and get something out the other end that doesn't read like a poorly translated engrish technical manual? Or do they just

Only great masters of style can succeed in being obtuse. -- Oscar Wilde Most UNIX programmers are great masters of style. -- The Unnamed Usenetter

Working...