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

 


Forgot your password?
Close
typodupeerror
×
Science Technology

DARPA Project Babylon: Universal Translator 325

Posted by michael from the unleash-the-kitty dept.
silance writes "Take a look at this project from DARPA (Defense Advanced Research Projects Agency)! This time the boys are trying to hammer out a portable, two-way, real-time, multi-lingual audible speech translator proposed to be run on everything from PDA's to wearable military hardware to workstations (to replace their PRE-EXISTING ONE-WAY real-time hand-held audible translators, of course!). The site contains descriptions of technical approaches, a technical milestones timeline, and a nifty Power Point presentation for the executive-types ;) They should give William Shatner a beta model out of pure respect... Here's a link to Google's cached HTML version of the Power Point presentation just in case. (P.S. - get a load of that logo at the bottom of the page!)"
This discussion has been archived. No new comments can be posted.

DARPA Project Babylon: Universal Translator More

DARPA Project Babylon: Universal Translator

Comments Filter:
  • babelfish... proving yet again that sci-fi steers science and innovation. ;)

    universal translator? i wonder if any trekkies patented it, or if it's even patentable?

  • pattern recognition? (Score:4, Interesting)

    by Telastyn ( 206146 ) on Wednesday May 29, 2002 @07:32PM (#3605992)
    The next big thing I think would be a "smart" translator that can do pattern recognition and "learn" as it gets more of the language. IIRC This is how the star trek translators work.

    Kind of the difference between pattern checking, and anomaly detection in virus scanners.
    • Expert-systems are still in their infancies. It's possible that advances in expert systems will allow for some kind of dynamic/fuzzy parsing. The real problem is that semantics (meaning) is more difficult to translate between languages. It means that to do really good translation requires a cognitive model (a brain or an approximation of a brain).

      • Re:pattern recognition? (Score:4, Insightful)

        by NanoGator ( 522640 ) on Wednesday May 29, 2002 @07:46PM (#3606084) Homepage Journal
        "The real problem is that semantics (meaning) is more difficult to translate between languages"

        Agreed. What will probably happen is that people will initially have to be trained to use these machines. "Instead of using the term 'kicks ass' (which will translate as abusing a donkey...), use the term 'defeat'."

        • Re:pattern recognition? (Score:5, Funny)

          by Phanatic1a ( 413374 ) on Wednesday May 29, 2002 @08:05PM (#3606184)
          Instead of using the term 'kicks ass' (which will translate as abusing a donkey...), use the term 'defeat'."

          Which will translate as "I am going to chop off both of your feet."
          • Heh, I haven't heard Benny Hill humor in a while...

            Speaking of semantics, I remember one time a coworker of mine was sick. A friend of hers asked if I could take the sick girl home. I told her I had no idea where I'd keep her.
        • 'kick ass'
          Eng->Ger: tritt Esel
          Ger->Eng: donkey steps

          via the fish
        • Agreed. What will probably happen is that people will initially have to be trained to use these machines.

          Initially, you're probably right. But in the future, a sweet advancement of these translators would be to include phrases like 'kicks ass' that aren't literally translated, but instead have a different connotation. This could get a little tricky though, because when translating back and forth you would have to decide whether to use formal translations (e.g. "It would please me for us to defeat the enemy") or informal ones (e.g. "Let's kick the enemy's fucking ass"). People who are bilingual may have already noticed this issue; I speak both Spanish and English, and I have noticed it myself when speaking with people who only speak Spanish.
    • The next big thing I think would be a "smart" translator that can do pattern recognition and "learn" as it gets more of the language. IIRC This is how the star trek translators work.

      No. The Star Trek translators work by mapping concepts in the mind of one being to concepts in the mind of another being. If you don't believe me then watch the Star Trek (The Old Series) episode "Metamorphosis." [ericweisstein.com] Kirk explains the technology behind the Universal Translator to Zephram Cochrane.

  • mmm...... (Score:2, Funny)

    by El_Nofx ( 514455 )
    I wonder if it will do Klingon to Romulan
    or maybe haXor to newbie

  • Obligatory B5 reference (Score:4, Funny)

    by Eimi Metamorphoumai ( 18738 ) on Wednesday May 29, 2002 @07:34PM (#3606001) Homepage
    The Babylon Project was our last, best hope for peace.

    Well, someone had to say it.

  • Re:DARPA Project Babylon (Score:5, Funny)

    by rmohr02 ( 208447 ) <mohr.42@osu. e d u> on Wednesday May 29, 2002 @07:35PM (#3606006)
    Here's a link to Google's cached HTML version of the Power Point presentation just in case.
    Darn--I could've done some decent karmawhoring giving out that information.

  • Re: (Score:2, Interesting)

    by account_deleted ( 4530225 )
    Comment removed based on user account deletion

    • Re:umm the logo (Score:5, Insightful)

      by lostchicken ( 226656 ) on Wednesday May 29, 2002 @10:04PM (#3606690)
      I guess it's the most sickening yet use of the "terrorist" catch-word for getting public support.

      This is quite offensive.

    • Re:umm the logo (Score:2, Insightful)

      by Giddeon ( 252506 )
      Presumably they are trying to paralell the tower of babylon and the twin towers. Supposedly, the tower of babylon failed because the builders could not speak to one another.

      Their logo seems to be implying that sept 11 could have been prevented with better communication and understanding of language. Like the TOB, the WTC might not have fallen if people could actually speak to one another (or gather better intelligence, or not anger other nationalities, etc, etc). The 'remember' at the bottom also seems to back this up - trying to tie the lessons of the past to the events of the present.

      It's the fire-breathing cat I can't figure out.

  • Strikes me as fishy (pun unintended) (Score:3, Insightful)

    by Seth Finkelstein ( 90154 ) on Wednesday May 29, 2002 @07:40PM (#3606050) Homepage Journal
    Look at this passage in http://www.darpa.mil/ipto/research/babylon/approac h.html [darpa.mil]
    (emphasis added)

    The task goal is to produce ten working two-way prototypes from each of four teams by the end of 18-months. The languages that will be translated are Farsi, Dari, Arabic, Pashto, Mandarin, and Uzbeki.

    Does this set off alarm bells for anyone? Those are complicated languages, and I believe Mandarin in particular is EXTREMELY tonal (i.e., doesn't work well in speech recognition).

    Look, just imagine which you get out of Babelfish. Now take it a few levels up, to speech. Does this proposal in any way sound achievable? (again, pun unintended)

    Sig: What Happened To The Censorware Project (censorware.org) [sethf.com]

    • Re:Strikes me as fishy (pun unintended) (Score:4, Funny)

      by cpeterso ( 19082 ) on Wednesday May 29, 2002 @07:50PM (#3606102) Homepage

      The task goal is to produce ten working two-way prototypes from each of four teams by the end of 18-months. The languages that will be translated are Farsi, Dari, Arabic, Pashto, Mandarin, and Uzbeki.


      DARPA might as well say:

      The task goal is to produce a working two-way prototype from each of four teams by the end of 18-months. The languages that will be translated are English and Godless Terrorist.
      • Awh, cmon. There's just not enough qualified translators out there that speak those languages and actually want to work for the government.

      • Re:Strikes me as fishy (pun unintended) (Score:4, Insightful)

        by MythosTraecer ( 141226 ) on Thursday May 30, 2002 @02:19AM (#3607586)
        The task goal is to produce a working two-way prototype from each of four teams by the end of 18-months. The languages that will be translated are English and Godless Terrorist.

        Incorrect, and unfair. Many of the "Northern Alliance" spoke Pashto and/or Dari (which is a dialect of Farsi). Uzbekistan let us use their military bases during the invasion of Afghanistan. And several of our allies, both real and on paper, speak Arabic.

        This is not a "English vs. Godless Terrorist" issue, as you say. The simple fact is there is a dearth of US military personnel that speak these languages, and we have an urgent need, now more than ever, to communicate with people who speak these languages. We do indeed have to spy on our enemies that speak in these tongues, but we also have to accurately share information and intelligence with our allies.
    • Sounds like a project equivalent to going to the moon ten times. This project will go for about 10 months and probably petter out. If they get it working, it will require as-of-now undeveloped algorithms in the realm of fuzzy pattern-matching, expert systems w/ learning and signal processing. Good luck.
      • I think I know of a way to speed up the process. A (voluntary) selective breeding program supplemented by some genetic engineering where we breed a really race of small humans who can fit inside something the size of a walkman. These nano-people would be given full scholarships to majr in as many languages as possible. We can also train them in Navajo and use them for encryption.

    • Re:Strikes me as fishy (pun unintended) (Score:4, Insightful)

      by gwernol ( 167574 ) on Wednesday May 29, 2002 @07:52PM (#3606115)
      The languages that will be translated are Farsi, Dari, Arabic, Pashto, Mandarin, and Uzbeki.

      Does this set off alarm bells for anyone? Those are complicated languages, and I believe Mandarin in particular is EXTREMELY tonal (i.e., doesn't work well in speech recognition).

      It is an interesting choice of languages for two reasons
      • As you note these are difficult languages to tackle. However this is the defense advanced research project agency. Their mission is to push the edge of what is technically possible and encourage new research. You do this by picking hard problems that haven't yet been solved.

      • Look at the countries involved. Twenty years ago this list would have been headed by Russian. For better or worse, it very much reflects (IMHO) the countries currently posing a threat or potential threat to the US.
      • Look at the countries involved. Twenty years ago this list would have been headed by Russian. For better or worse, it very much reflects (IMHO) the countries currently posing a threat or potential threat to the US.

        More importantly, it reflects the people that our soldiers most urgently need to be able to talk to overseas. It also reflects the lack of readily available translators to translate these rare, unique languages for those soldiers.
      • DARPA expects most of their projects (more than 80%) to fail. They fish around for that Amazing Thing that Might Work, and fund it. It's really cool.

        Even if this project fails, interesting knowledge will be gained. That's what DARPA's about, at least in part.
    • Actually, once they learn to play with it, I'd expect that the tonal form of Mandarin would probably make things easier... They'd allow you to split the language into 4 pieces -- up down flat and hook. Once done, you could then resolve the sounds and ignore the tone. I'd have thought that resolving the tonal direction of a sound would be pretty easy.
      • I'd have thought that resolving the tonal direction of a sound would be pretty easy.

        In the abstract, sure, but what about regional variations, with things changing slightly every few kilometres, and cumulatively changing a lot over distance? Call it the dialect problem.

    • Does this proposal in any way sound achievable?

      Not unless they solve the general AI problem first. In other words, no. You need a machine with a HAL-like intelligence to do good real-time translation. The machine will need to go to school for a few years to learn the idiosynchracies of each language and culture. No way this technology can fit into a portable translator given the current state of computer technology. Besides, even human beings have a hard time interpreting languages that they are fluent in.
    • "Those are complicated languages, and I believe Mandarin in particular is EXTREMELY tonal (i.e., doesn't work well in speech recognition)."

      I remember reading some years back that Mandarin was actually particularly well suited to recognition for exactly that reason. Makes sense if you think about it because some ambiguity is removed, ie there is no 'meet-meat-mete' in Chinese.

      LEXX
    • These are essentially the same goals that were set forth decades ago. This is a very hard endeavor, and while noble, I really wish they'd be a bit more realistic. I'm in the academic research world and this particular subject is what I plan to work in for my doctorate. Based on my perliminary background work, the state of the art in MT (Machine Translation) has moved forward significantly, but there is still a LONG way to go. To give an example, very good speech recognition (accuracies of 85% and above) and MT have been realized for limited domains. An example is the CMU plane ticket reservation system. MIT is working with MandarinEnglish translations in a ticket reservation scheme (and having some inside knowledge from both universities, I can say that the systems are impressive, but still a far cry from the wishes of DARPA). The MIT system, while the English speech was definitely computerized, the Chinese was sufficiently good that if I hadn't known that it was being synthesized, I would have had a difficult time guessing except for the fact that some of the translations were a bit off. Not necessarily wrong, but just the particular word choice sounded odd. Continuing, to give an idea of what problems researchers are tackling, Consider just the recognizer part of the system. Imagine the vocabulary set needed to work with the afformentioned domains. It's very limited, moreover, the syntactical structure of the language is also very constrained. And mind you, this is all being done on some high end workstations and servers. And they want to do this on PDAs? Not anytime soon. I'm all for this research because I love languages, but I would say that the type of system that these guys are describing would take at LEAST 15 years to get to and that's if there are some major breakthroughs very soon. So don't get your hopes up.

  • Concerns... (Score:3, Interesting)

    by NanoGator ( 522640 ) on Wednesday May 29, 2002 @07:44PM (#3606066) Homepage Journal
    It's cool that they're working on this and all, but their promises of building these into PDA's set off a flag in my mind. There's another company that, as of a couple of years ago, had developed a realtime program that allows one to speak english into a mic and have spoken japanese come out.

    I remember reading that they needed serious processing power and RAM to make this work. (At least 512 megs...) It seems like if one language takes up this amount of resources, then it'll be a while before we have a multi-lingual PDA...

    Maybe their technique is different? I dunno. I know it's not the same company.

    I guess I'm just concerned about this being vaporware.

    • Re:Concerns... (Score:2, Funny)

      by Anonymous Coward
      I once read (I forget where) that computers keep getting faster, and today's machines are more capable than what you could get a few years ago. I'll try to dig up the reference...
      • That was a nice attempt at trying to make me look bad, but you failed. Here's what I said:

        "I remember reading that they needed serious processing power and RAM to make this work. (At least 512 megs...) It seems like if one language takes up this amount of resources, then it'll be a while before we have a multi-lingual PDA..."

        Notice that I didn't say 'never happen' or 'impossible'.
        • That was a nice attempt at trying to make me look bad, but you failed.

          Actually the AC succeeded quite well.
          • Um right. He restated what I did, but in such a way to make it sound like he was arguing with me.

            "It seems like if one language takes up this amount of resources, then it'll be a while before we have a multi-lingual PDA..." In other words, PDA's will be able to do it in the future.

            "I once read (I forget where) that computers keep getting faster..." In other words, PDA's will be able to do it in the future.

            So no, he didn't succeed. Sorry.
    • I work for UCSB for Murat Karaorman (the head of the CS department for the College of Creative Studies and now an employee of TI), who worked on that project. They took 2nd place at a techno-fair for most impressive technology behind the technology that was called Digital Versatile Disks. It required a Sun server farm (and well in excess of your 512 Megs of RAM). Exremely cool stuff. Their demo was unrigged, members-of-the-audience style. The thing had a sizeable vocabulary. The company he worked for killed the technology, though. Maybe you read about something different, I'd be curious.

  • The USMC model (Score:3, Funny)

    by r_j_prahad ( 309298 ) <r_j_prahad AT hotmail DOT com> on Wednesday May 29, 2002 @07:47PM (#3606087)
    So... now every USMC ground-pounder will be able to say "die, motherfucker, die" in 32 different languages?

    Awesome.
    • hehe.

      and the other important phrases too:

      "another beer please"
      "bitch, suck it"
      "drop your weapons and come out with your hands up"
      "get some"
      "where is the toliet?"

  • Nice (Score:3, Interesting)

    by Auckerman ( 223266 ) on Wednesday May 29, 2002 @07:47PM (#3606091)
    Initial impression: boy are they in a hurry. Very aggressive time table for this project. 6 Months to "Emergency DARPA", 18 Months to 3 functional prototypes.

    Then I saw what languages it will have: Arabic , Mandarin (the part of china that border Pakistan and India is mainly Islamic), Pashto (Pakistan/Afganistan), Dari (Iran/Afgan/etc)

    Oh. What I want to know is what those 8 other languages are that they want to have the ability to add to it later?
    • At the moment, they only have codenames:

      RESERVED_ENEMY_1
      RESERVED_ENEMY_2
      RESERVED_ENE MY_3

      ... etc.

      :/

    • I know I'm mostly repeating what was implied by above poster, but this timetable could mean that something bad may be about to happen starting in 6 months and getting to full-scale whatevering in 18 months between the speakers of these languages.

  • Give it to Hoshi (Score:4, Insightful)

    by darkonc ( 47285 ) <stephen_samuel AT bcgreen DOT com> on Wednesday May 29, 2002 @07:55PM (#3606130) Homepage Journal
    They should give William Shatner a beta model out of pure respect...

    I'd much rather see them give it to Linda Park (Hoshi Sato on 'Enterprise'). She's the one who really made the universal translators famous. On TOS, the concept was mostly ignored ("They always worked perfectly -- Yeah! That's the story!"). On Enterprise, she does the translating almost as often as the translator does.

    Besides, I'd much rather see her recieving the thing in a newscast than Shatner (she's cuter!).

    • Re:Give it to Hoshi (Score:5, Interesting)

      by uebernewby ( 149493 ) on Wednesday May 29, 2002 @08:10PM (#3606207) Homepage
      True. Hoshi's fiddling with the universal translator really made me think about that piece of equipment we've been taking for granted in previous Star Treks.

      Seems my university syntax and phonology courses weren't *that* useless after all...

      The way I see it: suppose Chomsky's Universal Syntax turns out to be not innate to human brain structure, but to the very essence of communication. Meaning: if you're going to communicate something, all the forms you're going to be able to do it in will conform to a fairly basic set of ground rules and all the intricacies of natural languages are simply icing on the cake, as it were. If you figure out what that Universal Syntax is (sorry, I forgot the exact term he used - it's been a while, and my university education was in Dutch), you can feed that into a computer and teach it to reduce all phonemes from a given language to it. Then you can have the computer expand the basic message back into coherent communication in another language using the same basic rules.

      It's late. And when it's late, this is the kind of stupid stuff I think about.

      Oh, and I don't think Hoshi's *that* cute.

      • Re:Give it to Hoshi (Score:3, Informative)

        by darkonc ( 47285 )
        Oh, and I don't think Hoshi's *that* cute.

        Compared to Shatner?? Are you crazy?

        Actually, if you watch closely, she hasn't quite got the bust of T'Pol, and she rarely gets the sexy scenes, but she's still quit nice... and far more attractive (in my mind) than Shatner.

        If you remember the scene in the (one of) the first episode where Hoshi, T'Pol and Tucker are resting in decon, I thought both of the women were pretty nice.

      • If you figure out what that Universal Syntax is (sorry, I forgot the exact term he used - it's been a while, and my university education was in Dutch), you can feed that into a computer and teach it to reduce all phonemes from a given language to it.

        Syntax is not nearly enough. Unless you know what the individual words mean, you're shit out of luck. As an example, linguists pretty much had the syntax of Egyptian hieroglyphics figured out, but it took the discovery of the Rosetta stone for them to begin to understand what they were reading. Even then, there is still stuff they can't figure out. Something similar (old Spanish/Maya lexicons compiled by missionaries) was required to decipher Mayan symbols.

    • Re:Give it to Hoshi (Score:2, Offtopic)

      by dimator ( 71399 )
      I'll second the "cute" thing. They knew what they were doin when they picked the female cast members this time around.

  • Isn't anybody going to comment on it. DARPA has been getting their ass kicked because of it....

    I'm the last person to be offended, but even i think i'd in poor taste.
  • Why not Nichelle Nichols? After all, Uhura [uhura.com] was the communications officer.

    And if you want to talk about universal translators in sci-fi, Larry Niven's version was much better done in the Ringworld series. It didn't just magically make everyone speak English (or Interworld or whatever), it had limitations too: it had to listen to the foreign tongue for some time, to learn a minimal vocabulary, before it could begin communicating, which it did only haltingly at first. It sometimes couldn't translate words like <something> for which it had no context to deduce meaning. These limitations made for some interesting moments like the time Louis Wu had been captured by a woman who didn't talk much, and so he had to bide his time until the translator finally heard enough words to learn her language.

    But then again, the Ringworld was unstable...

    --Jim

  • interesting logo, but bad. (Score:3, Interesting)

    by Artifex ( 18308 ) on Wednesday May 29, 2002 @08:02PM (#3606167) Journal
    The "Babylonian" reference may at first seem apt: the towers were built 'to the heavens' (well, pretty high) and a lack of communication and understanding among peoples led to their downfall.

    However, the underlying, unspoken subtext of a comparison between us and Babylon is that we displeased God. Remember, in the Bible at least (there's other versions in other histories/religions), God was displeased, and the language confusion among the peoples was caused in order to bring us down.

    What this logo basically tells the world (or at least those who have an understanding of the mythos) isn't that we're a great nation and metter communication would have helped us - it's that we went against God, and this is how we paid.

    This sounds a lot like those right-wing extremists who tried to blame the attack on 'communists' and homosexuals in our country making God upset.

    Now, I feel, like many people do, that our country has done a great many things wrong: setting policy based on oil needs and not human rights, keeping some smaller countries' governments (including some democracies) destabilized in order to serve our own interests, etc. However, just as I don't think that we can claim "God is on our side," neither do I think anyone can claim that God isn't.

    This logo is offensive. That it shows the half-thought-out mentality of some of the people in charge at our governmental agencies should be a cause for alarm, not applause. We have been called Babylon by many people with grievances against us, and it seems our leaders are reveling in the name.
    • I used to work on a NASA research project, and the building we worked in had a large sculpture of Icarus outside the backdoors. At first I thought it was a poor choice, but now I think it is well placed and powerful, serving as a constant reminder against technological hubris, or at least using wax in heat sensitive projects.

      In the biblical myth of the tower of Babel, god introduced multiple languages to prevent people from working together. If you ignore the whole sinners-working-against-Yeowah angle, this DARPA project is basically allowing better communication and cooperation, overcoming the obstacle god enforced at Babel. Factor in the fact that much of the current round of fighting/terrorism is the result of religious convictions (or just "god"), and you've got a deep, thoughtful, and symbolic choice for title art.

      Of course, somebody probably just thought it looked cool, but...

  • I've been hitting reload hoping that somebody will post some links to the real-time one-way translators which were mentioned in the post... anybody have some information on said devices?
  • DARPA has been funding in one way or another [nap.edu] the premiere researchers in speech recognition, Dr. James and Dr. Janet Baker. Perhaps DARPA should have shown a little more foresight before the Bakers were permitted to sell off Dragon Systems to the Belgian corporation Lernout & Hauspie, which subsequently collapsed in bankruptcy amid fraud allegations, auctioning off [informationweek.com] assets such as Dragon Systems to ScanSoft, a Xerox spinoff.

    If DARPA doesn't in the name of national security (look at the languages that are the candidates for the initial Babylon competitors) simply override what noncompete clauses, patents, etc. that would keep the Bakers from working full-time on this project then they have learned nothing from almost decades of the Bakers' kicking the ass of the entire speech recognition community with their superior statistical approach. Unfortunately I suspect that various government regulations would not permit DARPA to pay a fair market value for the Bakers' services. This to me illustrates how far the United States has fallen from any capacity to mobilize the scientific and engineering community for modern equivalents to the Manhattan Project, except for medical technology.

  • Cached Version Fix (Score:2, Informative)

    by Grip3n ( 470031 )
    Looks like the link to the Google cache version of the document is in error. Here [google.ca] is the correct link
  • Bleh, color me impressed when they get plain old speech to text translators that can translate my ENGLISH into ENGLISH text.

    Until then I will be VERY skeptical about any vocal to vocal translators.

    I have tried out every generation of speech to text consumer software since 1990, and so far is has all been crap. Even if the government has technology that is 2x what the private sector is at;

    well hell, 2x ~10% is still pretty darn shitty and NOT something to be relied on in times of war.

    Bleh.

  • Doesn't anyone remember the addendum to the babelfish?


    ''Meanwhile, the poor Babel fish, by effectively removing all barriers to communication between different races and cultures, has caused more and bloddier wars than anything else in the history of creation.''

    we're doomed. I'm taking names for a bus to mars.
  • If you look at the first page of the powerpoint file, it contains a picture (Bruegel) [mexplaza.udg.mx] that shows the likely outcome of this project. An ambitiously large tower, abandoned and crumbling.

    The picture was obviously taken from a painting of the Biblical Tower of Babel [newadvent.org] story. Given the state of AI, I predict about as much success for this project.
  • A St. Petersberg company called Ectaco has already done this for bidirectional English-Russian handheld speech-to-speech translation. [ectaco.com] They call their stuff "Universal Translators" too.

  • Translation, slang and learning the language (Score:5, Insightful)

    by theolein ( 316044 ) on Wednesday May 29, 2002 @10:35PM (#3606837) Journal
    I am impressed with the attempt to try to get a two way translator packed into a little box, but I don't think it's going to be much of a success. I gather the sudden need for computational translation is because the military simply has too few people who speak the languages of the areas that they cover. I also assume that this is in direct relation to the FBI/CIA etc requesting Pashto and Arabic speakers to come forward and help them after 9/11 last year and the difficulties in understanding a lot of the folk in Afghanistan who speak three major different languages (Pashto, Dari and Uzbek) with a whole bunch of dialects.

    Sadly I think that it will be a waste of time. I speak six languages and at least one of them, Swiss-German, is not even a written language and here in Switzerland there about three major dialects of the language, some of which are not 100% mutually intelligible, and this in a Swiss-German population of about 5 million. I think that this system will run into the same sort of problems with languages like Arabic which has enormous dialectic variations in dialects say, from Algeria to Syria and people from the various areas can often not understand one another well. No one speaks classical Arabic of the Quran in day to day language use.

    My guess is that the Military/CIA etc would be better advised to simply get people to learn the languages and to train others in using day to day expressions. This would have, amongst other things , the positive side effect that soldiers (some of them at least) would be better able to understand the culture and the situation of the local people where they are stationed. Not only this but people in all the countries I've lived in have reacted much, much better to me when I've tried to learn their language instead of being the usual culturally ignorant Anglo Tourist who expects everyone to speak English. I would argue that the general western ignorance (especially amongst English speakers) is one of the causes of the percieved arrogance seen by many third worlders. Another positive effect of learning the languages would be that there would be someone who would understand slang, as I think there's nothing like a bit of slang to throw off any translation software.
    • simply get people to learn the languages and to train others in using day to day expressions.

      It depends on the task. You can't teach 100,000 people "day-to-day" skills in 80 languages. You can however issue 100,000 PDA's and create 80 translation programs.

      When Estonia unexpectedly declares war on Ziare you can download the Estonian and Swahili programs onto the 100,000 PDA's. The translation quality may suck, but you can instantly put 100,000 functional people on the ground.

      -
  • I'll wait for DARPA (or maybe USAMRIID [army.mil]) to develop translator microbes [scifi.com] for instanteous communication.
  • I wonder if this Universal Translator will handle the canine [cellar.org] language...
  • The sad part about them having all this cool stuff is that their webserver runs on NT. :)

    From netcraft.com. The site www.darpa.mil is running Microsoft-IIS/5.0 on Windows 2000.

    Wonder if their translator thingmy is going to be Microsoft BobXP

  • They should give William Shatner a beta model out of pure respect..

    If I recall the Trek backstory correctly, Spock's mother (a human woman) was the inventor of the universal translator. (And saved the show - no more needing to find planets where convergent evolution led to English-speaking neo-Romans.)

    So give a copy to Nimoy as his inheritance. B-)
  • Look. The military doesn't want to translate literature with this thing. They want something just good enough that US soldiers can communicate with the locals at a very basic level. It may be a struggle to communicate, but that's acceptable.

Slashdot Top Deals

Solutions are obvious if one only has the optical power to observe them over the horizon. -- K.A. Arsdall

Close