'Tower of Babel' Translator Under Development

monopole writes "The BBC is reporting on a bilingual translator under development by Carnegie Mellon University which senses sub-vocalized speech, recognizes it, translates it and then synthesizes the translation. The overall effect would be to dub the speech of the speaker."

Comments

The science behind it is fascinating

[chowdy]

The Tower of Babel Translator is small, yellow and leechlike, and probably the oddest thing in the Universe. It feeds on brainwave energy received not from its own carrier but from those around it. It absorbs all unconscious mental frequencies from this brainwave energy to nourish itself with. It then excretes into the mind of its carrier a telepathic matrix formed by combining the conscious thought frequencies with nerve signals picked up from the speech centres of the brain which has supplied them. The practical upshot of all this is that if you stick a Tower of Babel Translator in your ear you can instantly understand anything said to you in any form of language. The speech patterns you actually hear decode the brainwave matrix which has been fed into your mind by your Tower of Babel Translator.

Re:The science behind it is fascinating

[buswolley]

I'd love to have the president wear the translator so we'd know if he believes the bull too.

Re:The science behind it is fascinating

[Anonymous Coward]

HEY DON'T SAY THAT... RAH-RAH-RA-RA "BIAS" RA RA RA RA "Gosh, that's just despicable, this is the best President we've ever had" RA-RA-RA-RA! BIAS, BIAS, RA RA. Just listen: http://images.usnews.com/usnews/news/articles/0610 25/061025baronebush-hi.mp3

Re:The science behind it is fascinating

[fohat]

whoever modded the parent down should be the first against the wall when the revolution comes...

Re:The science behind it is fascinating

[WoLpH]

We already have something like that, right?
It's called a universal translator

Re:The science behind it is fascinating

[BakaHoushi]

Ironically, the Tower of Babel, having removed all barriers of communication on the planet, has been the cause of more bloody wars than anything else in history.

The Tower of Babel, being so mind bogglingly useful and improbable, has also been used as the final, clinching proof of the non-existance of God. The argument goes something like this:
"I refuse to prove I exist," says God, "for proof denies faith, and without faith, I am nothing."
"But the Tower of Babel gives it away, doesn't it?" says man. "It proves you exist, which, by your own logic, means you don't."
"Oh my, I hadn't thought of that," says God, and quickly disappears in a puff of logic.
"Oh my, that was easy," says man, and for an encore, goes on to prove black is white and is promptly killed at the nearest zebra crossing.

In all seriousness, putting our towels to the side for a second, doesn't anyone find the name ironic? I mean, I'm not a religious scholar, (I'm agnostic) but wasn't the Tower the CAUSE of different languages in the Bible? They wanted to build a tower to Heaven, so God supposedly made everyone on it speak a different language so they couldn't finish their work, I believe. (although I suppose they could have just as easily come up with a system of hyroglyphics or other pictorial ways of communicating what needed to be done. Though maybe the problem was that some languages sounded kinda similar, so one person's "Get to work, now, you lazy bum" is another man's "Go home and get some rest, we'll send you your checks tomorrow, you sexy stud."

Re:The science behind it is fascinating

[CmdrGravy]

You'd have thought that having spent quite a long time building the tower already and given the likleyhood that the intention was to just keep building up in the same way the lower floors had been built the workers would have been at the job for long enough to pick up what they were doing and how the process worked so as not to need much in the way of any further communication.

Also since it's highly unlikely these bronze age tower builders were ever going to build anything even half the size of buildings like The Empire State Building or mountains such as Mount Everest just how high off the ground is heaven actually situated that God is worried the tower will reach it ?

Personally I am coming to the conclusion that the bible is just a load of old bollocks and "God" is just some kind of made up figure people can use to justify their stupid actions.

Re:The science behind it is fascinating

[ch0knuti]

The point is not in the height of the tower. It's the symbolism that man was defying God and trying to get "there" by his own means.

Re:The science behind it is fascinating

[nospam007]

>...In all seriousness, putting our towels to the side for a second, doesn't anyone find the name ironic? I mean, I'm not a religious scholar, (I'm agnostic) but wasn't the Tower the CAUSE of different languages in the Bible? They wanted to build a tower to Heaven, so God supposedly made everyone on it speak a different language so they couldn't finish their work, I believe.
---
Mmm, large building projects have that problem until this very day, they only call it sub-contractors nowadays.

Re:The science behind it is fascinating

[jools33]

Great! If this works on Vogon we can kill off our poetry recital audiences with internal heamoraging!
http://en.wikipedia.org/wiki/Vogon_poetry

Re:The science behind it is fascinating

[stunt_penguin]

Yes, but will the revolution be televised?

Re:The science behind it is fascinating

[Skye16]

So if I try to get there by jumping real hard, he'll cut my legs off?

Sweet. Nice guy.

Re:The science behind it is fascinating

[blippy]

The practical upshot of all this is that if you stick a Tower of Babel Translator in your ear

No, no, you're thinking of a babelfish. The Tower has to be inserted up a completely different orifice.

Re:The science behind it is fascinating

[Anonymous Coward]

So if I try to get there by jumping real hard, he'll cut my legs off?

Effectively? Yes. However, the decision to exceed your specifications was yours...

Re:The science behind it is fascinating

[CmdrGravy]

Well that makes no sense at all, if God didn't actually mind how high the tower was then why would he have taken steps to make sure it didn't get any higher ?

No doubt these dedicated tower builders would still have been trying to build their towers even given the supernaturally imposed communication difficulties so God hasn't in fact stopped anyone trying to do anything, he has just stopped them from succeeding which would suggest that it was the success of such an enterprise he was worried about rather than the idea behind its inception.

Re:The science behind it is fascinating

[ch0knuti]

Well the way I read it is that by stopping the construction of the tower he displayed the futility of the idea to defy him. (Sort of like Bill Gates :) )

Re:The science behind it is fascinating

[mikael]

so God hasn't in fact stopped anyone trying to do anything, he has just stopped them from succeeding which would suggest that it was the success of such an enterprise he was worried about rather than the idea behind its inception.

He should have filed patents and brought patent infringement lawsuit like everyone else.

Planet Earth 1
God, et al. Year 0

Abstract

A tower being is provided for the means of reaching heaven constituted by a plurality of stone columns and support beams positions on top of each other. The tower comprises of an architectural assembly omposed of a large number of levels constructed from stone columns reinforced by stone beams. Each floor may be augmented by mud bricks to provide additional reinforcement against strong winds. Access to each level is provided through
either a wooden ladder or a mud bricks staircase.

Re:The science behind it is fascinating

[Morphine007]

I'ma go out on a limb here, but do ya think that perhaps the bible is mostly allegorical? I mean, I'm no theologist, but it would seem to me that the tower of babel story is more of a warning to the masons of the time that if they try to build too high, they'll be fucked.

I would think that the "message" from "god" is closer to "you don't understand my creation well enough to build this yet... in time you will..."

Then again, maybe I'm just a heathen...

Re:The science behind it is fascinating

[siriuskase]

He probably just didn't like the idea of the entire human race ganging up together on this project. The height of the tower doesn't matter, or we wouldn't have skyscrapers or space shuttles, etc. So what is it about universal cooperation that is threatening?

Re:The science behind it is fascinating

[COMON$]

How you got modded 5 informative is beyond me. Insightful maybe, but informative no.

While an intelligent assumption for a person who has not delved into the history of the bible, it is however mostly wrong.

The allegory belief usually comes when one distances himself from the Bible. The less you read it (be you agnostic or Christian) the more likely you are to believe that it is allegorical and disjointed.

The bible is at best a historical account of a group of people through their eyes, thus needs to be viewed as such, and the writing is protected by God. At worst it is an accurate mythological history book.

I am not a theologian or historian, just a geek but I am fascinated with the bible's accuracy Historically, they may embellish stories to include God, but the time line is accurate and the Historical places and people are real. Which is fantastic when you consider the age of the book.

In conclusion I would say that the tower of babel story is not allegorical, but rather God chose that junction to disrupt the human race long enough for them to define themselves rather than playing silly games that he told them not to. Whether we like Mosaic law or not, even as secularists we have to admit, there is a bit of unnatural wisdom in the protection offered by Mosaic law.

Re:The science behind it is fascinating

[CmdrGravy]

You know what they say; "divide and conquer"

I think Gods just running scared and GW is his one chance in a million last throw of the dice.

Re:The science behind it is fascinating

[kefoo]

You're forgetting that the translator feeds on the brain wave energy of the speaker. In the case of the president it would starve.

Re:The science behind it is fascinating

[ebyrob]

Actually.... if you read the account it says God was pissed because:

1) God told man to spread out and fill the earth.

2) Man arfed around on some tower instead of spreading out and filling the earth.

If you read what happens after the "event"...

3) Man spread out into groups that could talk to each other and filled the earth.

So really it didn't have much at all to do with people "getting somewhere" just them being stupid/disobedient. I'm sure someone could have had a lot of good laughs over the fact the humans thought they were going to "get to heaven" when not only would they have to get into space, but heaven is actually in another dimension/lightyears away/otherwise inaccessible to mere mortals. (Or simply doesn't exist... I guess that'd be pretty ironic too.)

Other Languages

[Longfinger]

If this technology gets good enough, none of us would ever need to learn a second language. That would be a bad thing, right?

Re:Other Languages

[Anonymous Coward]

If this technology gets good enough, none of us would ever need to learn a second language. That would be a bad thing, right?

I think that's kind of like saying that if calculators get good enough, no one needs to know math anymore.

In fact, this will probably be used in many of the same places - anywhere you'd find a cash register, you'll probably find automated translaters. You won't see them used in academia or in diplomacy, though.

Re:Other Languages

[Anonymous Coward]

This could be a terrible thing. Learning another language teaches you a lot about a way a culture thinks.

Re:Other Languages

[nebaz]

Why would this be a bad thing? I'm all for diversity of culture, but experiencing that diversity would be much easier if we all understood each other.

Re:Other Languages

[kfg]

Language is not composed of words. It is composed of idiomatic phrases (idiomatic phrases do not mean what the words mean) only understandable in context. True automatic translation is not possible.

As an example, I was once called upon to translate the simple advertising slogan "Si Misura" from Italian to English. This had already been translated as "Made to Measure."

Quick, without thinking, tell me what the product was?

If you're a native English speaker you probably think of a suit or dress. Maybe a kitchen cabinet. Some tool with human ergonomic requirements.

The product was a liquid chemical compound, so I translated it into the correct English idiom for such; "Custom Blended."

And with that simple example we haven't even touched on issues of syntax yet; or more complicated issues of social usage (say formal vs. informal forms).

KFG

Re:Other Languages

[Anonymous Coward]

While understanding each other is a good thing. It's a fact that languages are different so a translation isn't really the true meaning of what the person said, it gets the message across but due to language vocabulary, and structure, and culture what the person's actually saying is often different from the translator. Uhg... that didn't come out in a very coherent fashion. What I'm trying to say is that while something like this (that actually worked) would be GREAT, there's still reason to actually learn another language.

Re:Other Languages

[antifoidulus]

But doesn't the language itself play a part in the culture? Almost any language you look at there are bound to be words that don't translate well because the object or action or emotion in question is so innately bound to the culture that they made a word for it, but to other cultures the concept isn't all that common so they never made a word for it.

Also, even translation by the best humans still destroys a lot of the subtlety and beauty in a language. It's a best a piecemeal game. Hell, most novels/tv shows are not even translated literally, some artistic liberty is usually taken to make the work "flow" in the language it is being translated into. Translation is great for contracts or technical documents, but if you really want to understand a culture then you need to learn its language.

Re:Other Languages

[JuzzFunky]

Second Language? You might not even have to larn a first language! Just grunt. Mm.

Re:Other Languages

[servognome]

This had already been translated as "Made to Measure."... If you're a native English speaker you probably think of a suit or dress. Maybe a kitchen cabinet. Some tool with human ergonomic requirements.

Unless you're a /. nerd, in which case you probably think of a pill or a pump

Re:Other Languages

[brian.glanz]

There are practical advantages in problem solving which have been tied to the language used in mental formulation, for example the development of what is metaphorically called "logical circuitry" has been shown to diverge between native English and Mandarin Chinese speakers.

My expectation is that spoken language will eventually go the way of handwriting: creature comfort, dying art, what once defined the best of us but becomes in many cases an indulgent inefficiency. How?

Anybody who dares to at this point, has realized they can jam wires into the human brain and let it learn to control machines on the other end. It's already beyond that in fact, with embedded communication devices being the next step, stepping shoe now currently in air: you'll see in a few days in Nature how real the "Neurochip" already is.

People should stop pretending this is about helping paraplegics by playing Space Invaders or moving a cursor with mind control, or that we're only trying to help brain injury, stroke, or paralysis patients. This is about construction workers with better than human strength in their better than human limbs. We drive vehicles through obstacles on land at 10 times the speed human beings can run, and we fly vehicles at 800 times the speed we can biologically move ourselves. We are mentally capable of managing bodily abilities far beyond those with which we are born.

This is not only about helping the disabled, and it's not only about incredible speeds or strengths. It's also about perfectly able people who would rather control personal electronics with their thoughts than search for or decipher other remote control electronics. Personal electronics are going to be a lot more personal, too; these people will eventually prefer to have personal electronics embedded in their bodies and networked with their minds.

Don't worry about losing human language: we will only lose it when we'll be better off for it, when we communicate and think better without it. The translator here, with IBM and elsewhere is of course more narrowly focused, but with this we are converging on technological telepathy and obsoleting human language.

Human logic and good intentions have come at it from a more traditional, less technological direction, giving us Esperanto, Loglan, Lojban, etc. You've probably heard of only one of these, which you probably laughed at somebody for being Geek enough to know any of. Most of them have been great ideas and well executed, but despite inherent gains in efficiency or intellectual force they are nowhere near the markets and their returns depend on mass adoption. Technology is different, it's tied directly to markets and to private profiteering with immediate amplification of wealth among the wealthy. Human beings are not going to create a better enough language, soon enough, before we create a technology which in itself superior to all human language. BG

Re:Other Languages

[Anonymous Coward]

Si esta tecnología fuera bastante buena, nadie aprendería una segunda lengua. Eso sería una mala cosa, la derecha?

Re:Other Languages

[Jugalator]

This translator wouldn't help in written communication, and perhaps not even over telephone due to the crappy input quality. So the severe limitations that would imply in at least business relations would be so bad that you'd still need to know the language.

This could be nice for the occasional trips to other countries or if you have some friends/relatives in another country where you for that sake don't want to learn their language. But in both these cases, you usually don't know their language today either and just try with your English (regardless if having that as your native language or not).

Re:Other Languages

[AhtirTano]

Language is not composed of words. It is composed of idiomatic phrases (idiomatic phrases do not mean what the words mean) only understandable in context.

That's like saying humans aren't composed of cells. We are composed of organs who's functions are not useful in isolation. Idioms are composed of words, and the words are vital. Just like an organ will cease to work if you change the component cells, the idiom will cease to mean what you want it to if you change the component words.

True automatic translation is not possible.

True automatic translation will be possible when we have true artificial intelligence. And not a day sooner. (But maybe a day or to later.)

Re:Other Languages

[timeOday]

True automatic translation is not possible.

"True" is your trump card there. (I'm not so sure "true" tranlation is possible at all, even by a human translator.) But they may very well achieve a level of performance which is useful, which is all that matters.

Re:Other Languages

[kfg]

. . .the idiom will cease to mean what you want it to if you change the component words.

Exactly.

True automatic translation will be possible when we have true artificial intelligence.

What is the English word that equals the Greek word "logos"?

KFG

Re:Other Languages

[suv4x4]

If this technology gets good enough, none of us would ever need to learn a second language. That would be a bad thing, right?

I wouldn't worry about it. Our speech and phrasing ability, languages: they are not something you can isolate and reproduce in a program, without reproducing much of the rest of the intelligence of a human being.

Subtle phrasing, context.. We learn new ways to express ourselves all the time, and we can do so since we put what we hear to an intelligent analysis and processing. A computer can add words and phrases to its dictionary, compare how similar they are and so on, but eventually it not as intelligent as a human being..

So: we'll always have to learn other languages, until AI shows up. They we may need not to learn anything at all :D

Re:Other Languages

[Anonymous Coward]

Gentlemen, prepare your tinfoil hats!

Re:Other Languages

[Anonymous Coward]

What is the English word that equals the Greek word "logos"?

the Word

Re:Other Languages

[Anonymous Coward]

Nice try, http://babelfish.altavista.com/ But I'm not buying it.

Re:Other Languages

[Anonymous Coward]

You miss the point. There is no single translation of logos, "word" is the most basic translation, but often, you will need to translate it as "reasoning" or "argument" to make the translation sound correct in English.

Having said that, I think even without true AI, the context can be guessed at, maybe from a frequency database (especially for popular idioms), with a reasonable accuracy.

And, finally, "the WORD" would be "ho logos", not just "logos" (if you were trying to invoke the Word that has become Flesh).

Re:Other Languages

[klang]

Spanish in Mexico is different from Spanish in Spain. English in America is different from English in Great Britan.

This is "the context" of the language, the part of the language that can only be translated, if you have intimite first hand knowledge of the two languages you whish to translate between. Basically, you have to know what moves in a society to truely understand the language.

Learning a second language is one thing, using it and understanding "the context" is something else and I think that a making a true Babel machine includes something close to an artificial sentinence, that can keep track of "the context" of several languages and several locations, to truely work.

A vocabulary of 100-200 words with an accuracy of 80% .. Anybody could get to that point from a 5 hour crash course on any language .. In fact, I think that accuracy would probably be higher for translations between "related" languages (based on Latin) .. But I am sure that a course on Chineese or Japanees could get to the same point.

(I am tri-lingual)

Re:Other Languages

[rHBa]

I won't have to larn a frist linguage wunce I instorl firfox 2

Re:Other Languages

[FST777]

On top of that, it's a proven fact that children who are raised bilingual have less learning troubles in the future (even in math and science). That could well be because his/her level of understanding is being developed from a young age due to learning two (or more) languages.

That could be an argument against using this device on a broad basis (since it destroys the need and foremost point of raising children multilingual), but on the other hand this device could be used to teach and learn languages too.

Re:Other Languages

[Fred_A]

What is the English word that equals the Greek word "logos"?

Duh, that's easy, it's "small plastic brick" even kids know that !

Re:Other Languages

[DDLKermit007]

Exactly...I'm learning Japanese right now and hooooly shit is there no way on Earth a computer will be able to reliably translate even proper statements (or at least within my lifetime). The language is way too heavily situation based. Theres a number of ways to say anything with many different levels of politness. You have to be able to think the culture to do things even somewhat reliably. Which is true for any 2nd language. Hell even going from US English to UK English can be an experience in itself.

Re:Other Languages

[sharkey]

You might even get your own TV show!

Re:Other Languages

[drsquare]

Translation is great for contracts or technical documents, but if you really want to understand a culture then you need to learn its language.

What if you don't want to understand a culture, just understand what someone's saying? Unless you're going to speak it for the rest of your life, learning a language is pointless, as you'll just forget it.

Re:Other Languages

[Explodicle]

Keep in mind there's only one math, and it makes sense. There are thousands of langages, and none of them make any damn sense.

Re:Other Languages

[Shaper_pmp]

You can't fully understand what someone's saying unless you understand their cultural context, and how it differs from your own.

For example, what's the difference in (UK) English between: "I couldn't care less" and "I could care less"? In US English they're used interchangably, but in UK English they're opposites. There are many such words or phrases in the English language alone where the precise word chosen (or connotations of a word) totally changes the meaning of the entire phrase, even reversing it's meaning.

Another example would be a simple phrase in US English like "he was pissed"? US meaning is "he was angry". In UK English it means "he was drunk", and a word-for-word translation into greek it would be meaningless (the equivalent idiom in Greek would be something like "he took it on the skull").

Seriously - if you ever want to understand the drawback to automatic translation, try getting two Greek friends to talk colloquially to you, but translating each individual word into English - it's completely unintelligible.

Re:Other Languages

[AlecC]

Fine - provided you are willing to be limited to a vocabulary of 100-200 words, according to TFA.

Speech recognition for limited vocabularies has worked quite well for a long time, but quud quality real speech recognition is still over the horizon.I think this will go the same way.

Re:Other Languages

[Chabil Ha']

Which is unfortunate. As a trilingual person (I guess you could add a dozen or more if counted computer languages) I have gained quite a richness of life and human understanding from learning another's language. There are many idomatic expressions that may seem a little funny initially, but after some thought, really seem to make you look at the world in a different way.

For example, in the Mayan language K'ekchi', the term "Ma cuan sa' a ch'ol xbanunquil _________?", literial translates to mean Is it in your heart to do _________? which idiomatically means, "Are you willing to do ________?".

By not learning another's language, you lose an opportunity to look at the world through the 'eyes' of that language.

Re:Other Languages

[ashooner]

What about the fundamental issue of grammar? How is a (subject)(verb)(object) language going o be translated live into a (subject)(object)(verb) language? Or the old "The man bites the dog" example from introductory german class. Perhaps this can be done, but there is going to have to be some temporal caching...

Re:Other Languages

[schon]

There are thousands of langages, and none of them make any damn sense.

What about Esperanto? :)

Re:Other Languages

[bdonalds]

How is this any different WITHOUT a babel fish? If you are speaking to someone in a language that isn't their native tongue, shouldn't you try to avoid idiomatic expressions anyway?

Re:Other Languages

[Morphine007]

/sigh.... especially esperanto....

Re:Other Languages

[Anonymous Coward]

Keep in mind there's only one math, and it makes sense.

There are many maths - many branches of mathematics, many coordinate systems, many equivalent formulations of the same idea, but many sets of postulates (imcompatible!),. They are all logical...but that doesn't mean they're easy to understand, translate, or automate. We've not had much luck developing a calcalator that can prove things for you.

Re:Other Languages

[Morphine007]

You make a really great point, but it's not entirely the one you were trying to make ;-)

In Canadian English(TM) "I could care less" and "I couldn't care less" are used interchangeably as well. "He was pissed" means both, though. And that, I think, is the massive stumbling block in any automatic translator: Language tends to be situationally dependent. If you go to your average Canadian and, with no context, say "Man, was Frank ever pissed last night", he'll likely assume that you meant drunk, because of the context which "last night" provides. But even still, they might ask: "What? Pissed, as in drunk, or pissed, as in pissed off?"

There's just too much contextual information that is passed in your average sentence. And let's knot get into the problems that homynyms wood pose two people.... I recently had to think about what I was going to do as my Comp Sci M.Sc. thesis project... I've alluded to why I'm staying the fuck away from Natural Language Processing. I wish these guys all the luck in the world, they're going to need it.

I'm sure with a little more thought, you guys can come up with other colloquialisms that mean very different things depending upon the context. Hell, I was watching Discovery: Japan a while ago, and I remember them saying something about the Japanese word that is used to respond to a request for food. Ie. if someone asked you if you wanted to hit subway, and you did, you would say this word.... the problem is, if you change the inflection of the word ever so slightly, it means the exact opposite... tough problem, indeed.

Re:Other Languages

[Dark_MadMax666]

uhh don't confuse math with arithmetic. And yes nobody needs to do calculations by hand anymore - we have everything from calculators ,to data centers for crunching numbers. And if translators are good they will be used everywhere -from tourists to diplomats.

Re:Other Languages

[Dolly_Llama]

Not when you have an accountant as good as mine.

Re:Other Languages

[Lord Ender]

True automatic translation is not possible.

Like almost everyone else who has said "...is not possible" before you throughout history, you are wrong.

Suppose there are a finite number of idiomatic phrases, and database space is cheap enough to be effectively free.

Someone could compile a database of all idiomatic phrases and simply map between them in any two languages.

I think the real reason translation hasn't taken off yet is because people keep trying to come up wiht better algorithms, when what they really need is a moderately-sophisticated algorithm and a fantastically large database. The algorithm would just serve the purpose of being able to generalize parts of some of the idiomatic phrases so that the database is kept to a managable size.

I can understand why you would want to think translation is not possible, as you have been paid to do translation. But I am confident that cheap databases will be the answer to the problem.

Re:Other Languages

[Lord Ender]

translation by the best humans still destroys a lot of the subtlety and beauty in a language

Moving in to homes destroyed the subtlety and beauty of cave-dwelling. I don't see you living in a cafe.

Re:Other Languages

[Lord Ender]

what's the difference in (UK) English between: "I couldn't care less" and "I could care less"? In US English they're used interchangably

I think there are two types of people: Those that use language soely as a collection of sounds, and those who think about the actual meanings of the actual words they use.

I consider the first group to be, on average, dumber than the second. And they are the only ones who say "could care less." So, while you say they are used interchangably in the US, this is only done by the dumber section of our populace.

I had a roommate who only understood English phonetically, and if I were to ask him to find an error with my sig, he would have been totally unable to do so. For that reason, I did not let him do any of the writing for our group projects :-)

Re:Other Languages

[antifoidulus]

You are right, the coffee costs too much and the wifi gets way too bogged down to do serious porn surfing.

Re:Other Languages

[Anonymous Coward]

> I.E. if someone asked you if you wanted to hit subway, and you did, you would say this word.... the problem is, if you change the inflection of the word ever so slightly, it means the exact opposite... tough problem, indeed.

You don't mean hai vs. iie, do you? They're pretty different if you listen closely, but they're somewhat similar.

Re:Other Languages

[Lord Ender]

Oh, bugger off. The "f" is right next to the "v" on a keyboard. Punk.

Re:Other Languages

[Morphine007]

I'm not sure, they did say that it was the exact same word, and it was just the inflection that was changed. It was on TV though, so who knows how accurate it actually is...

Re:Other Languages

[tepples]

Suppose there are a finite number of idiomatic phrases

Suppose there are a potentially infinite number of situations in which a given phrase could mean one or the other thing.

Re:Other Languages

[identity0]

No, it's just a case of a phrase becoming an idiom, where the literal meaning of the words has little to do with the actual meaning of the whole phrase.

I think you will find that there are lots of idioms in the English language that have a well understood meaning, but which most people could not tell you how the words actually lead to the meaning.

"The proof is in the pudding"
"He had a devil-may-care attitude"
"She dressed to kill for the party"

Besides, "I could care less" is actually correct, people usually can :) It's "I couldn't care less" that is incorrect, because the fact that they are talking about it means they care to some extent :)

Re:Other Languages

[zobier]

Besides, "I could care less" is actually correct, people usually can :) It's "I couldn't care less" that is incorrect, because the fact that they are talking about it means they care to some extent :)

Bzzzt.

Sorry, but if I couldn't care less then I'm already caring the least that I could. It's usually the other person in the conversation that's talking about it. What are you going to do, ignore them?

Re:Other Languages

[Anonymous Coward]

uhh don't confuse math with arithmetic

I wasn't. In fact, that was the point of my analogy - if arithmetic were all of mathematics, then calculators could do basically any math we'd ever need. But it isn't; they can't. I expect these translators to be similarly limited.

And if translators are good they will be used everywhere -from tourists to diplomats.

Good luck with that...

Re:Other Languages

[CryoPenguin]

More likely "ee" vs "iie", though I seem to remember there was a pair even closer than that.

Or just consider the english equivalent: "u-huh" vs "uh-uh". Imo, those fit the bill of meaning "yes" and "no" and differing only in inflection.

Re:Other Languages

[Shaper_pmp]

Yes you should try to avoid idiomatic expressions, but:

1. People won't always do that - some idioms are so common they're easy to accidentally drop into conversation even when you're trying not to.

2. Idioms are just the most obvious example of the problem. Homonyms, connotations and the like can still cause problems.

3. I'm not sure where the Babel Fish comes in, but since it works on unconscious brainwaves it's likely that it communicates translations of meaning, rather than word-for-word translations.

Re:Other Languages

[Shaper_pmp]

IIRC, Japanese is one of those languages (like Mandarin or Cantonese?), which only have a few vowel sounds, but about half a dozen inflections and tones that totally change the meaning of words.

Re:Other Languages

[Shaper_pmp]

"No, it's just a case of a phrase becoming an idiom, where the literal meaning of the words has little to do with the actual meaning of the whole phrase."

That's true, but idioms can come about by people just constantly and persistently using the wrong words. And there's a difference between idioms which use language incorrectly, and ones which we simply don't remember the origin of.

For example, there's nothing wrong with using the phrase "the whole nine yards", since it implies there are nine yards to be had, so using the whole nine yards is using 100% - the intended meaning of the phrase.

On the other hand, "the proof is in the pudding" is meaningless gibberish - the proof of the pudding is in the eating" is the correct idiom, meaning the only real measurement of worth is the results something gives, not how it looks or any other property of it.

Likewise, people say "I could(n't) care less" when they're dismissing something and not worth caring about.

"I couldn't care less" means literally that I am unable to care any less than I do about the matter. I literally care the minimum amount it's possible for anyone to care about anything.

"I could care less" means that it's entirely possible for me to care less about the issue, directly implying that I do care about it to some degree.

Since with the phrase you're trying to dismiss something as not worth caring about, stating that you do in fact care about it is the exact opposite of the sentiment you're trying to convey.

Re:Other Languages

[Anonymous Coward]

This works, if you make the assumption that all languages are effectively static. You'd also need to figure out which dialect is in use, and so on and so forth.

It might be possible if you built some kind of wiki database, but you'd be stuck in a state of perpetual catch-up. Not to mention all the garbage data that gets in.

Furthermore, what do you do when you run into languages that do not map 1:1 idiomatically? Some languages simply don't have the constructions that other languages do. Not to mention languages that are drastically different in terms of syntax and so forth - for example, a number of East Asian languages don't have verb tenses.

Building a translator between similar languages is probably possible, but it may well be impossible to build a truly universal translator.

Re:Other Languages

[Anonymous Coward]

...and in fact, none of them make sense

Actually, "none" takes the singular "makes"

Which is amusingly a spot-on comment for this thread :-)

Re:Other Languages

[BytePusher]

A calculator is used to assist mathematical thought. A calculator is a kind of language interpreter. In higher math, hand calculators are rarely used because calculations are rarely carried out to actual numbers. More often computers are used exclusively to view the expression of mathematical thought. I heard a quote once, "Language precedes thought." I believe it is the basis for some psychological theory. However, it seems clear to me that thought produces language. If the goal is to express thoughts and if computers can accurately express thoughts from one language to another, then why not use computers for that task almost exclusively? This would be wonderful, as an emphasis could be placed on beauty of thought rather than how it is expressed. In much the same way mathematics is able to focus and grow in beauty or eloquence as a result of computer aid.

that's awesome

[Anonymous Coward]

chinese people can now speak like poorly dubbed kung-fu movies in real life!

Re:that's awesome

[Anonymous Coward]

Finally! My dreams have come true!

subvocalization

[TubeSteak]

http://en.wikipedia.org/wiki/Subvocalization

Subvocalization is basically micro-movements of the muscles associated with speech. The Wikipedia article mostly focuses on reading & subvocalization, so I wonder, do you have to be trained to do it consciously?

http://en.wikipedia.org/wiki/Subvocal_speech_recog nition

This wikipedia article says that recognition is hard.

Re:subvocalization

[Anonymous Coward]

I beg to differ. Subvocalization (the inner-voice) is likely an internal mental process which is closely connected to the neural mechanisms used for muscle control used in vocalization. There is likely a priming effect where muscle responses trigger easily, but not completely, resulting in micro muscle movements.

Am I making this up?

Re:subvocalization

[Frogbert]

Well luckily I've changed the article, so now sub vocal recognition is easy

Re:subvocalization

[RuBLed]

okay.. it's easy now

Re:subvocalization

[Instine]

What would make it even harder is your brain would be trying to figure out what the 'noise' was every time you opened your mouth. Wouldn't a sound cancelling mask w mic embeded be more sensible. As the tech is there already. The tech they should be working on is THE TRANSLATION as I've yet to see 'good' English to anything machine translation....?

Encore

[locokamil]

... and for an encore, he proved that black is white and went and got himself killed on the closest zebra crossing.

universal translators, here we come!

[yincrash]

we are that much closer to the future.

Remind me to turn this off at work

[Joebert]

Electrodes are attached to the neck and face to detect the movements that occur as the person silently mouths words and phrases.

It's only a matter of time before this thing gets me fired.

New Headline:

[Shadyman]

'Tower of Babel' Translator Under Development, translating fish unavailable for comment

Just like the Ferengi....

[meatflower]

Once this technology gets finalized and then made tiny we can implant them in our ears.
Of course we'd have to avoid any and all Theta radiation or they'd start malfunctioning. I don't know about you guys but when Rom was trying to find the reset button on Nog's translator implant during episode #77 of DS9 it looked pretty painful.

Re:Just like the Ferengi....

[Anonymous Coward]

Just don't keep that video tape in your mom's basement too long. Moisture's not good for those things.

I don't get this

[thewils]

Neat idea, but how can it possibly translate a Subject, Verb, Object language into a Subject Object Verb language, like English to Japanese, immediately? I'm learning some Japanese and it's difficulty partly lies in the mindset required to switch a sentence round and finish with the verb - a really simple example would be something like "It is hot" which becomes "hot is".

Also, how does it distinguish synonyms which have a completely different translation in another language?

Expect to get punched a lot when using this device on your first trip abroad. Especially if the locals you meet aren't using one too.

Re:I don't get this

[Anonymous Coward]

Hate to break it to you dude, but if you think switching the object and the verb around is hard, you probably aren't cut out to learn the language. That is probably the EASIEST part of the language.

Re:I don't get this

[Anonymous Coward]

But doing it instantly (as this device is supposed to do) would be hard.

Re:I don't get this

[thewils]

Well, I was trying to give a simple example. It can get quite convoluted. Check out Mark Twain's essay on the Awful German Language.

"The Germans have another kind of parenthesis, which they make by splitting a verb in two and putting half of it at the beginning of an exciting chapter and the OTHER HALF at the end of it."

Re:I don't get this

[TwilightSentry]

Check out SHRDLU; it's a natural language parser which simply understands grammer by going through a set of rules.

Re:I don't get this

[bangenge]

dude, if you're learning japanese, then you will (if you haven't already) learn that determining subjects, objects and verbs are very easy with the use of their particles. arguably, the most difficult part of the japanese language is vocabulary and probably verb conjugations, not sentence patterns.

Re:I don't get this

[Bueller_007]

Japanese verb conjugation is simple. It's the agglutination that makes things difficult.

Re:I don't get this

[zanderredux]

Let's see....

English... 30 hours.

French... 30 days.

German... 30 years.

Chinese, arabic or any other language with impossibly hard scripts... 30 centuries?

Re:I don't get this

[anders_dj57]

Would the order matter? Most people seem to understand what Yoda saying is!

Re:I don't get this

[Eli Gottlieb]

Except that Arabic script is actually alphabetic, not composed of ideograms.

Question of the Millenium

[richdun]

So let's say this works - which language will we use as a primary one now that it doesn't matter, since everyone can understand everyone else easily?

Anyone who has studied languages knows (not "no"s or "nose") that English absolutely sucks (as in is bad, not as in pulls air into itself), but we use it widely (as in across a large range of people and places, not as in having a large girth) in large part (as in a significant reason, not as in being a big piece of something) due to the primary sources of finance and technology being in English-speaking countries (not literally the countries, but their people).

I like the idea, and see the huge, positive social impact it could have, but I feel sorry for the guy/gal responsible for it to test its ability to translate into/out of English.

Re:Question of the Millenium

[davidsyes]

Aw (not as in awe-struck...) shucks (not as in stripping corn stalks) you're such cunning linguist....

Re:Question of the Millenium

[maglor_83]

I lost you when you started talking about the primary seasoning or relish served as an accompaniment to food.

Re:Question of the Millenium

[Anonymous Coward]

English doesn't suck. It may be difficult for computers to process, but that isn't the only quality of a language.

Verbing nouns, for example, is good shit.

Re:Question of the Millenium

[jbrader]

Here in America we always hear how lucky we are to be native English speakers because it's such a difficult language, but I've talked to numerous people from Russia, China, the Netherlands, Mexico, Germany and France and they all told me it was fairly easy.

Re:Question of the Millenium

[AhtirTano]

Sorry to say, English is not as unusual as you would like to believe. (I am a linguist.)

In many ways, English is quite simple. For example, our word order is very straightforward. I work with a language were the following is a normal sentence: "This is city New called York here." (This city here is called New York.) In fact, almost every permutation of those words would be valid without a change in the basic meaning (as long as "is" is the second word). This is a so-called non-configurational language. Parsing English is easy by comparison.

I work with another language were there is a slight stress difference between the sentences "That might be true" and "He's honestly picking his butt." The words "soup" and "shit" are differentiated by a 40-50% increase in the length of the last vowel. There is one word for both "blue" and "green", and another word for "yellow", "orange", and "brown".

As to the likelihood of this project succeeding anytime soon: Languages are often not directly translatable into each other. One language I work with has an entire part of speech I cannot adequately translate into English. I have to wave my hands and point to convey the same information in English.

Re:Question of the Millenium

[Anonymous Coward]

Anyone who has studied languages knows (not "no"s or "nose") that English absolutely sucks (as in is bad, not as in pulls air into itself), but we use it widely (as in across a large range of people and places, not as in having a large girth) in large part (as in a significant reason, not as in being a big piece of something) due to the primary sources of finance and technology being in English-speaking countries (not literally the countries, but their people).

Uh-huh... English sucks. That's an extremely ignorant comment. Most of the "examples" that you posted are actually examples of the STRENGTHS of English. And if you had "studied languages", you would know that they are common to most languages in the world.

We use the word "sucks" metaphorically. Metaphors and richness of language are a STRENGTH, not a weakness. We can say "English-speaking countries" as a shorthand for "countries in which the majority of the population speak English". Allowing people to be succinct when they speak is a STRENGTH, not a weakness. We can use the word "part" to represent both a fraction of something intangible, and a piece of something tangible. They're both basically the same, so not having to learn a separate word for each of these cases is a STRENGTH, not a weakness.

English's irregular spelling presents a challenge, but would you prefer the Japanese orthographic system, possibly the most complex in the world? And compared with Vietnamese pronunciation, English is a breeze.

Seeing as English is one of the most widely spoken languages in the world, and the momentum it already has because of the reasons you mentioned, there's absolutely no reason that it wouldn't continue into the future. Who modded this shit up?

Re:Question of the Millenium

[AmberBlackCat]

I would think whatever language the presenter chooses would work fine, as long as the thing handles all of the languages anyway. But if they do have to settle for one language, how about that Klingon language? It could be justified because for not showing favoritism to any particular human language and would give a bunch of people who don't get sex something to brag about.

Re:Question of the Millenium

[schwieter]

Care to share which languages those are?

--

Re:Question of the Millenium

[spicate]

Aw (not as in awe-struck...) shucks (not as in stripping corn stalks) you're such cunning linguist...

Not as in what?

Re:Question of the Millenium

[vga_init]

I like English because of the breadth of vocabulary. It allows for a certain level of nuance that enables me to express myself precisely while using as few words as possible. Also, the grammar is pretty simple. Pronunciation is not hard either, but our writing system needs work! As long as you practice spelling, there is nothing that makes English spectacularly difficult compared to other languages.

Re:Question of the Millenium

[chgros]

Care to share which languages those are?
I'm pretty sure the second one is Chinese, from what I heard about it.
As for the first one, I don't know (Latin has this kind of property), but I'm quite surprised you could split up "New York"

Re:Question of the Millenium

[schwieter]

I'm pretty sure the second one is Chinese, from what I heard about it.

It isn't Mandarin, which I happen to be studying at the moment, since it the tone changes the meaning of individual words, not whole sentences. Furthermore, though I can't speak very much, I do happen to know my colors and all five listed have distinct words.

but I'm quite surprised you could split up "New York"

So am I. That's why I asked the question - I'd love to learn more about these languages, if only I knew what they were.

--

Re:Question of the Millenium

[thetroll123]

BZZZTTT!!!

widely (as in across a large range of people and places, not as in having a large girth)

Widely never means "having a large girth". That's "wide". But thanks for playing...

Oh, and it's MILLENNIUM. Hopefully people will get this over the next 993 years.

Re:Question of the Millenium

[ObsessiveMathsFreak]

I have to wave my hands and point to convey the same information in English.

How is this substantially different to the way the majority of native english speakers convey information?

Re:Question of the Millenium

[Anonymous Coward]

I think you're talking rubbish. Name them!

Re:Question of the Millenium

[herve_masson]

All very good points that make me think we are far away to see anything significantly useful in this field ;) I did not know that some language would use a unique word for distinct colours. Linguist job must be fascinating.

We could also add to this that accurate language recognition would require to deal with "context" to smooth ambiguities, which is where a human brain is performant (though this is not something we do easily) and a software + computer (of those days at least) very poor.

I really don't see any impact anytime soon, really, but I'm looking forward to be proven wrong.

Re:Question of the Millenium

[awol]

I am a native English speaker (well Australian anyway). Members of my familiy have taught ESL (English as a Second Language) to adults and children. Friends of mine are speech therapists. For the last 15 years I have been doing business with people who have English as their second language.

English is trivial to learn well enough to communicate. The reason? You only really need to learn vocabulary. All the points raised previously about the difficulty of automatic translation are kind of true but, for English at least (and probably Spanish), irrelevant. This is because these languages are the most accepting of inappropriate use. Actually from a linguistic perspective there is a lot of variation that can at least provide syntactic correctness and hence still convey meaning. There is very little (any?) positional context in English, ie where the meaning of a word or phrase changes according to its position in the stream. Indeed even where this might be the case it is really only in quite sophisticated use in which these things exist and that can be ruled out when you are communicating with an identified non-speaker. Also most of the speakers of English language are most accepting of inappropriate use.

Further the language positively rewards inappropriate use by the nature of English art (poetry, prose, even comedy) where so much of the beauty of are is derived from pushing the edge of meaning by interesting context. It is true that many languages are the same but perhaps none so much as English (perhaps with the exception of Arabic where it seems to me [I am not a linguist] that metaphor has a large role in even basic speech).

Having lived in London for 10 years, I regularly see non-native english speakers from completely different language families (Arabic, Chinese, Latin, Germanic, Asian, Slavic) speaking to each other in English (with varying levels of brokenness) because it is easy for them to find "common" ground to refine the synonyms they are using, even those that they do not all understand. (Sure they are in London, but even at conferences outside the UK the same is true). Part of this is because of the English as Lingua Franca but part of that is because English (as a language) is so tolerant of bad grammar. It is rare for bad grammar to fundamentally alter the meaning of a dialogue. It is possible and it is easy for confusion to arise, but then so too is it easy to clarify the actual meaning intended.

Many of the "this is impossible" comments from previous posters seem to assume that the translation described is context free. Why should it be so? The translator can just as easily be fed context about environment as well as the surrounding language of the segment being actively processed. Such information would help the translation.

So automatic translation can work (even badly) and provide a good basis for an iterative approach to conveying meaning between parties that have no common language. At a basic level even if it is just "identifiers" (nouns), "doing words" (verbs) and "describing words" (adjectives, or adverbs) it will facillitate _communication_.

Re:Question of the Millenium

[Sleuth]

Well, the early uses will more likely be in simple communication situations. In face to face attempts were people interact, you can go back and forth to come to an understanding. You don't need good context understanding in the translation, just some basic assistance in getting your meaning into the other persons language.

I'd guess there are tons of uses for that. Think of all the military interactions with foreign citizens. And aid workers interacting with foreign citizens. Even within a country, like here in the USA, were a public agency interacts with people speaking only a foreign language.

Re:Question of the Millenium

[elgatozorbas]

As for the first one, I don't know (Latin has this kind of property), but I'm quite surprised you could split up "New York"

They probably wouldn't do this becaus it is a name (novo Eboraco, btw), but in general adjectives can be separated from the word they refer to, to add some stress.

Re:Question of the Millenium

[AhtirTano]

Exactly! Tons of information we convey is done outside of the language we use. Some of the things we have to "leave" English to convey are simple words in other languages. How can automatic machine translation possibly work when that is the case?

Re:Question of the Millenium

[AhtirTano]

I did not know that some language would use a unique word for distinct colours.

Well, all languages do. The "red" of a rose and the "red" of a brick are quite distinct colors, but we just call them "red". There are languages that make fundamental distinctions we do not in English. Really, it's all just wavelengths hitting our eyes. Different cultures have different ways of organizing that data.

Re:Question of the Millenium

[herve_masson]

Sure, I know that "close" colours can be referred from a single word (I don't know how many words we have for red variants we have in french, but that is likely at least a few dozen). You mention "blue" and "green": there must be a way to find them "close enough" to fit in the same word, but that's definitely a huge stretch from my own culture and language. Just by curiosity, which language is this ?

Re:Question of the Millenium

[thewils]

Dude is a linguist who confuses "were" and "where". Obviously not a very cunning one.

Re:Question of the Millenium

[CYDVicious]

There is one word for both "blue" and "green", and another word for "yellow", "orange", and "brown".

1. "Blue" and "Green" one word english translation is "Turqoise"

2. "Yellow, Orange, and Brown" one word english translation for all three would be "Shit" or "Zune".



~CYD

Re:Question of the Millenium

[zobier]

I have to wave my hands and point to convey the same information in English.

How is this substantially different to the way the majority of native english speakers convey information?

Actually, I think that's Italian.

Re:Question of the Millenium

[AhtirTano]

It isn't Mandarin, which I happen to be studying at the moment, since it the tone changes the meaning of individual words, not whole sentences.

The change in stress changes one word from a modal meaning "remote possibility" to a compound verb meaning "pick the butt". The adverb "honestly" and the verb "be true" are homophonous, and word order doesn't matter very much; thus, the ambiguity. This language is O'odham. The other language, the one that lets you split "compound words" is Serrano. Both are Uto-Aztecan languages spoken in the American southwest.

Re:Question of the Millenium

[AhtirTano]

Both languages I originally talked about it are the same for colors terms. They are O'odham and Serrano, both Uto-Aztecan languages of the American southwest.

Re:Question of the Millenium

[Eivind]

It's a hard task, I honestly don't think we're anywhere close to there yet.

Actually, it's *3* hard tasks.

First, the device needs to accurately recognize what you say (both the actual words, and the actual meaning) this is something which we don't have any software capable of doing well today, and doing it when the language is only subvocalised would be an order of magnitude more difficult.

Then, the device need to translate the statement into a foreign language, preserving meaning (not just statically replacing words which frequently completely misses the point). This is *also* something we don't know how to do really well today. We can do it so that the result is "understandable" for simple texts, but that's about it.

Third, the device needs to output spoken text in the foreign language. This is *also* something we don't know how to do terribly well, though I suppose the sub-task of these 3 that we've got the best grip on. Stephen Hawking has a device which performs only this function, and anyone who's heard him talk knows the state of the art on the field. (which is: easily understandable, nowhere *near* the fidelity of even someone with only a basic knowledge of a language)

Re:Question of the Millenium

[IncognitoCraven]

Khidir beneath Momouteh, that's what I always say.

Re:Question of the Millenium

[OodlesOfGerbils]

Out of curiosity, what are the two languages you are referring to? I'm a linguistics undergrad, so this whole conversation is pretty interesting to me.

Re:Question of the Millenium

[Anonymous Coward]

Blue and green share a Kanji in Japanese as well, though there are also distinct words. In general, blue vs green seems to be a rather blurry distinction, as compared to other cultural differences in color divisions.
http://en.wikipedia.org/wiki/Distinguishing_blue_f rom_green_in_language

Oh great...

[revlayle]

the last time i heard of people constructing a Tower of Babel, the whole world got toally pwned and no one could understand each other. well, not much different than it is now is it.

/not religious

Re:Oh great...

[aussie_a]

Apparently that happened about 2,000 years after the Earth was first formed. Considering that happened 4.57 billion years ago I find it appalling that only now are they attempting to translate the numerous languages that resulted from the Tower of Babel travesty. I mean, how lazy can you get? What have they been doing all this time?

Re:Oh great...

[Rebel_lord]

I was thinking the same thing.

Shouldn't the title read the Anti-Tower of Babel or Reverse Tower of Babel because it's helping people to understand each other despite their language barriers?

Re:Oh great...

[leuk_he]

The point of that story is (beside explaining why there are different languages) That overambitious project that do think man is all powerful might turn the world in a worse to understand place.

You might solve the language problem, but you will cause other problems.

Language is also the result of culture. You might make a universal translator/bablefish, but you will still fail to explain thing like spam to people who never have seen a computer.

my 2 cent.

Re:Oh great...

[CmdrGravy]

The Mine Of Lebab ?

Re:Oh great...

[jackbird]

explain thing like spam to people who never have seen a computer.

Or daylight to people work with them.

Simulated telepathy.

[EnsilZah]

I find that alot of my thought process is subvocalized.
I was wondering how hard it would be to translate that into audible words and transmit them at a volume relative to distance from the receiver.
Then you could have a social experiment where a group of people live together for a period of time while equipped with these transceivers.

Re:Simulated telepathy.

[Joebert]

Then you could have a social experiment where a group of people live together for a period of time while equipped with these transceivers.

I'm thinking more along the lines of Reality TV Show.

Ain't Going to Happen

[eean]

Don't worry, they've been working on machine translation since the 60s and fully automatic translation still sucks. Speech to text isn't so great either.

Language is complicated!

Re:Ain't Going to Happen

[Ougarou]

Nope, ain't going to happen.

Professor Schultz said: "The idea is that you can mouth words in English and they will come out in Chinese or another language."

He must know that language is more then just words, there is grammer to. Then there is a story line, context, etc. etc. Let alone the fact that most people don't finish their sentence when they are having a conversation (tape a conversation and check it).
And for those experts who said: it showed the technology was "within reach". Stop calling yourself expert, because this is like telling people: computers can play chess now, so they will probably take over the world in a few years.

Re:Ain't Going to Happen

[LiquidFire_HK]

Speech to text isn't so great either.

Dear aunt, let's set so double the killer delete select all.

Re:Ain't Going to Happen

[schon]

language is more then just words, there is grammer to.

Ther si alos speeling (which you might want to work at improving, considering you misspelled two words under five letters each.)

Re:Ain't Going to Happen

[bdonalds]

"He must know that language is more then just words, there is grammer to" Dont' furget that their's also speling!

Re:Ain't Going to Happen

[Ougarou]

Thets' knot insightfull, the hats just bunny!
I'll need two in stock a spelling checkers. Stop or try to batminton a speech recognizer.

Re:Ain't Going to Happen

[Anonymous Coward]

At the UN one afternoon:

1> Nice suit.
"Your fitting is good."

2> That is not funny.
"The humour fails."

1> I can't understand what this thing said for me in your language.
"I have lost the object in your language for the comprehension."

2> You crazy person?
"You are a mental disruption human."

Another WAR erupts soon afterward!!!

Re:Ain't Going to Happen

[Jinky Williams]

That got a solid "LOL" out of me. Thanks!

It also sounds like something I might find on VG Cats.

Re:Ain't Going to Happen

[Xtravar]

Of couse not. 1 has no oil worth taking.

Could be a huge improvement

[edwardpickman]

Any chance it could correct Bush's english? Could help the rest of us understand what's he's trying to say.

Re:Could be a huge improvement

[ooh456]

Sorry it doesn't work like that. Garbage in, garbage out.

Re:Could be a huge improvement

[RationalRoot]

That could make things WORSE.

let me be the first to say:

[monopole]

"All your base are belong to us!"

Re:let me be the first to say:

[Anonymous Coward]

What you say !!

Re:let me be the first to say:

[Psychotic_Wrath]

IT WORKS! 477 Y0ur 8453 4r3 8370n6 10 u5

Here's what you'll look like

[rhysjj]

Some photos of the electrode arrangement needed on the face:

http://www.flickr.com/photos/rhys/260069248/
http://www.flickr.com/photos/stasarama/245979951/
It's still a lab prototype of course, but a massively impressive one. I'm very pleased to see articulatory speech recognition (that's the main research area in this particular project, rather than the translation itself) get written up by the BBC.

Re:Here's what you'll look like

[scrote.sac]

Wicked, Rhys!

Especially with the Welsh captions, which entertained me no end.

Perhaps someone can make a 3-phase version of this for Professor Kevin Cyborg Warwick - would love to see what sort of sub-vocalisation 415 volts across hi face would generate!

Re:Here's what you'll look like

[SpinyNorman]

Doing speech recognition based on articulatory data is much easier than doing it based on spoken speech data... It'd be a speech researcher's dream if s/he could always derive accurate articulatory data from speech, rather than having to make do with an inaccurate mapping from the modulations of the glottal source that it produces (formants, fricatives, stops, etc).

Adding the translation step (which is doomed to be not much better than using a guide book to translate, given current levels of translation know how) is really a gimick, either to attract attention and get reseach funding, or based on some very limited domain (military?) that they are targeting.

Re:Here's what you'll look like

[rhysjj]

It's true that articulatory speech recognition should be easier than automatic speech recognition (ASR) based on waveform analysis alone. It's massively unfortunate that ASR research has, at least for the past 20 years, concentrated mostly on the latter and not the former. Janet Baker, whose MIT PhD introduced Hidden Markov Model (HMM)-based ASR, and opened the door to companies such as Dragon (which she and her husband founded), is herself now saying that HMMs are rubbish for speech recognition. I desperately hope that through this CMU project, and others, that people will start to take note of this.

I think you're entirely correct that the machine translation (MT) stage is a bolt-on in this particular project. This project is I think a vehicle for articulatory ASR rather than MT. But I wouldn't be so keen to dismiss MT efforts altogether. It's true that in some ways the current deployable systems make gross assumptions about language, which may be even worse than the assumptions ASR systems make about speech (that's particularly true of purely statistical MT systems). But Google and others have apparently shown that with a large enough corpus, you can get results that extend beyond simple phrase-book look-up quality.

There's one main question facing the researchers at CMU, I think. That's whether people will be happy to stick a dozen electrodes on their face in order to achieve speech-to-speech translation, or whether they'll prefer to speak into a microphone and have a speech synthesiser (e.g. the open-source Festival, partly developed at CMU) speak the result. I'm not entirely convinced they will, but I'd be absolutely delighted to be proved wrong.

Re:Here's what you'll look like

[SpinyNorman]

I hadn't heard that Janet Baker had said that about HMMs...interesting. Do you have a link or reference to the article where she said that, or any more information about why she said HMMs are inadequate and what alternatives she's proposing?

I'd have thought though that use of HMMs or alternate approaches is orthoganal to what features (articulatory vs cepstra, etc) are being used.. is it really HMMs themselves that she's panning?

Re:Here's what you'll look like

[Anonymous Coward]

Actually, it was Jim Baker's Ph.D. thesis (at CMU in 1975) that focused on HMM-based ASR. It appears that Janet's thesis (also at CMU in 1975) was more concerned with using time-domain features. I am admittedly less familiar with Janet's work, but I just went down the hallway to CMU's Engineering and Science library and took a quick look at both theses.

Form factor

[digitalhermit]

It would be cool if this technology could be designed into something like a hearing aid. It should probably be just large enough to be inserted into the inner ear canal. If it could interface directly with the auditory nerves that would be cool.. Sounds far off, but many current hearing aids can do this. We could put the microphone so that it's hidden completely. Hearing aids are useful, and nothing to be embarrassed about, but some people are self conscious about them.

It's not so far off to think that it could automatically decode not only language, but difficult expressions.. For example:
        Thy micturations are to me
        As plurdled gabbleblotchits
        On a lurgid bee.

That makes no sense, and is almost painful to hear, but the translation device could effectively render this to the equivalent:

      I all alone beweep my outcast state
And trouble deaf heaven with my bootless cries
And look upon myself and curse my fate,

Re:Form factor

[Lorkki]

If it could interface directly with the auditory nerves that would be cool.. Sounds far off, but many current hearing aids can do this.

It's called a cochlear impant and it's not quite as common as hearing aids are. Seeing as it requires surgery, replaces natural hearing and (currently) lacks in resolution, I wouldn't see it as very desirable unless you do have a serious hearing impairment.

more importantly

[Anonymous Coward]

Translation should be on the recieving end, not from the source.

Simply put- if one person is using this, then everyone in the room needs to speak either his actual language or the language that is coming out of the translater. In a room where there are more than three languages being spoken, it would fail to provide people with a translation.

On the otherhand, if it was on the receiving end (such as the babel fish), then the peron listening would hear everything in his own language and it wouldn't matter what anyone else was speaking.

tedivm

Measuring vs. Translation

[headkase]

This just pushes the measurements of a persons vocal output down to the muscle level instead of sound levels. There is nothing artificially intelligent about this - they've limited their translation to 100-200 words and those are probably straight-literal translations. So basically all that's new and unique about this device is that it reads muscle impulses. No advance in the state of intelligent translation at all. And that's probably because there is no fundamental understanding of thought. Yet.

It will never be completed

[Null Perception]

Soon the developers will start speaking java, perl and cobalt and fortran.

Translation:

[Aphex Junkie]

"Your basis everything belongs to us, it is!"

Re:Translation:

[Anal Cock]

You can do better than that. ;)

"Foundation it is complete spreads out and the dansles United States, them it belongs."

Communication != understanding

[schwieter]

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

From the "what if" dept.

[notenslaved]

I wonder what we'd hear if this was hooked up to a newborn... Well, besides "I just crapped myself!"

Re:From the "what if" dept.

[flyboyfred]

As the father of a newborn, I think it would translate roughly to this:

WAAAAAAA! WAAAAAAA! WAAAAAAAA!

Which is, of course, the same in all languages.

Could this allow the mute to speak?

[Allnighterking]

If it is using muscular sensors to "detect" sounds then wouldn't it be possible to create one that would allow the mute to speak? One would think that an English to English or Chinese to Chinese translation would allow then to perfect the detection process, and aid any number of people who can't for whatever reason speak but who can mouth words.

Killer App

[jshazen]

I can't believe nobody's posted this yet. This would be *really* useful as a *mono*-lingual translator! Build one of these into every cell phone, and suddenly I don't have to hear your inane conversation just because you happen to be sitting next to me in the plane.

This should be *much* easier to do that the version that actually translates, and it would add nearly as much to quality of life of the user and everyone else in his environs.

Re:Killer App

[Anonymous Coward]

Build one of these into every cell phone, and suddenly I don't have to hear your inane conversation just because you happen to be sitting next to me in the plane.

Probably you would have to make some kind of mask that plugs into the phone. That would be good because you wouldn't have to look at my face either.
Possibly you could make a phone that extended sensors to all the right places automatically and sort of clamped on. You could call it the "face hugger"

Computer translators will never work, unless...

[master_p]

Computer translators will never work, unless they can understood the context of the speech 100%...and this is impossible, unless the translator is fed all the knowledge of the speaker.

Translation is not a matter of algorithm, but a matter of data.

Re:Computer translators will never work, unless...

[Anonymous Coward]

Translation is not so much about the data, as it is about information, a fundamentally different concept. Focussing on information highlights that the required information that person A attempts to convey to person B is "coded" into data/speech in the sometimes vain hope that the same information will be regenerated or re-experienced in the mind of person B. This is describing semantic translation ... literal translation is always possible with a computer, and others have pointed out the sometimes hilarious consequences of "mis-translating" words and phrases that may not even have been well-expressed in the source language in the first place. Human translators need not worry about the computerised competition, not unless we humans ALL adopt "Simple English" and "Simple Chinese" and "Simple Maori" versions of our own languages, and that ain't happn'n any time soon.
Did you see the offer in the Canadian newspaper offering a "revendeur de drogues de neige", French for "reseller of icy drugs" ?
It started out as a "snowpusher" and the machine just "did it's job".

A bit of Calm Insense always required

[blahdeblah2000]

Wreck a nice beach? Americans already pretending to do this in Iraq Real-Time Computer-Based Translation in Iraq

Sub Vocalized speech?

[icebike]

What the hell is sub vocalized speech
  (he muttered)...

Continued..

[lobotomir]

The Tower of Babel Translator, by effectively removing all barriers to communication between different races and cultures, has caused more and bloodier wars than anything else in the history of creation.

translation, diversity, understanding

[zeromorph]

Well, the problem is that understanding someone is far more than parsing the other's sentences. It's getting to the point where you understand what meaning the other intended to convey. That's here all this machine translation still fails (and probably will fail for a long time to come). Because for that you need a lot of backround knowledge, you actually have to attune yourself to the experiences, the culture of the other. And that is a large part of what is learnt in a foreign language course.

All this automatic translation feigns that you understand the other, but actually your interpretation might be very different from the intended meaning. Sometimes a rough understanding might work, but mostly it you run into problems later. You might discover real referential differences, like you two where talking about wo very different things, but also interpretational differences or social misunderstandings which might result in severe discord.

A good way to test this are jokes, because they are such a condensed way of cultural meaning.

But this works also between varieties of one language, e.g English. Are you really sure an American fully gets what a upper middle class person from India is telling him/her about her feelings or experience, just because both of them have English as their mother tongue?

Understanding the other is an undertaking that costs a lot of effort and machine translation helps very little with that. Appreciating diversity, like appreciating everything else, demands effort and dedication and there is no short cut.

Re:translation, diversity, understanding

[Anonymous Coward]

This is an issue when people are from the same place, speaking the same language as much as it is in your example... so what's your point?

Why try to run before you can walk?

[nanoakron]

I guess they've perfected their translator that relies on actual vocalised speech then...

-Nano.

"My hovercraft is full of eels"

[shotgunefx]

Clerk: Ahh, matches!

Hungarian: Ya! Ya! Ya! Ya! Do you waaaaant...do you waaaaaant...to come back to my place, bouncy bouncy?

Clerk: Here, I don't think you're using that thing right.

Hungarian: You great
poof. Clerk: That'll be six and six, please.

Re:"My hovercraft is full of eels"

[nobelHubel]

Brilliant. This is the first thing that came to mind when I read the piece. God! The tobacconist sketch is hilarious.

arms wide open

[Anonymous Coward]

"Darmok, the beast at Tinagra"

"Shaka, when the walls fell."

Re:arms wide open

[IncognitoCraven]

Sokath, his eyes uncovered!

Re:arms wide open

[Anonymous Coward]

Darmak and Gilad at Tinagra

Well, except...

[Ogemaniac]

actual Japanese skip their particles all the time. Either way, translation would be somewhat slow, as you would have to wait for a Japanese to finish a sentence before you could start to translate it. In English, you need the verb right away, but in Japanese you are usually given it last. Many short Japanese sentences consist ONLY of a verb, where as the English equivalent would consist of a verb plus pronouns. To translate from Japanese to English, the computer would need to know the subject and/or object being referred to, without it being spoken. In other words, it would need to be able to understand context. This is incredibly challenging.

Rots o' ruck!

[FridayBob]

But, it'll never work. I worked on a translation program for several years back in the 90's and it comes down to this: to translate from one language to another you don't just have to understand the meaning of the words, but their context. And language just isn't logical. You can try and include lots of pre-translated phrases, but the combinations are infinite! In other words, the only way to solve this is to first create a real artificial intelligence... which may never happen.

Re:Rots o' ruck!

[SpinyNorman]

True in general, but in practical terms I bet that a really large database of pre-translated pieces, with suitable fall-back algorithms, could do very well, perhaps especially in more formal domains such as technical papers. Google is trying this approach, and apparently already do much better than conventional translation approaches using it. I'm waiting for them to take it out of the lab and use it to replace Bablefish or whatever they use on google.com.

Re:Rots o' ruck!

[argent]

Plus, this device will have access to someone who understands the language - the person speaking. If the person you're talking to doesn't understand, you can change the way you phrase the statement. With the right kind of feedback and some kind of cueing mechanism this could also turn into an effective aid to learning a language.

right now using it I am

[should_be_linear]

I have pedestrian system functionality connected automatically translate to Slashdot form you can digest in the moment as I am publishing onto vehicle summer program.

Management speak

[Sir Runcible Spoon]

Could it be used for direct translations into management speak?

"It is a crock of shit, and smells as of a sewer." -> "It promoteth growth, and it is very powerful."

Italian?

[Ruvim]

I have to wave my hands and point to convey the same information in English.

Must be Italian?

Warlpiri?

[OnTheWay]

Very interesting. Are you referring to Warlpiri and its sign language? I love what you said about "I have to wave my hands and point to convey the same information in English." That reminds me of the opening of Garcia Marquez' One Hundred Years of Solitude, where "the world was so young that many things did not have names, and in order to talk about them you had to point to them."

Re:Warlpiri?

[AhtirTano]

Are you referring to Warlpiri and its sign language?

I do all my work on languages of North America. Mostly, Southern California and Arizona, though I've dabbled in a language from Mexico and one from Oklahoma.

Re:Warlpiri?

[ceejayoz]

So what, you're not going to tell anyone what language it is?

Re:Warlpiri?

[Anonymous Coward]

Sadly, the name cannot be expressed in English.

Our linguist friend is frantically waving his arms and pointing but you don't seem to be getting the message!

Oblig. Python

[Aqua_boy17]

If tobaccanists get these, all requests to buy cigarrettes will translate as "My hovercraft is full of eels."

Shameless plug

[flokati]

I helped build the Tower of Babel

My nipples explode with delight!

[Anonymous Coward]

So who is writing the translations, after all?

of promise

[kevin.fowler]

this is like promising sound of futures. the translate will sense make contains great accuracy grammar.

Moo

[Chacham]

Easy enough.

You holf it next to your ear, and it keeps saying "42, 42, 42".

IAAEM

[Deliveranc3]

I am an English Major.

There are a few scary things about this, one we all learn the same language this will drastically affect the number of perspectives in the world.

While you may disagree I have a quote that can help explain one of my English Prof's said "The Most Important word in any language is representation."

Another scary thought is that people won't need to learn any form of common language, if this technology gets sufficiently advanced it could literally allow each person to have their own language which would make it FAR harder for people to relate to each other (Something which is already pretty damn difficult).

I used to be a huge proponent of Esperanto but dealing with literature and seeing how it relates to deep brain centres makes me a little more conservative about blithly changing people's native language.

Re:IAAEM

[pianowow]

You're an English major? I didn't even minor in English and I found 4 spelling/grammatical errors in your short post.

The Tower of Babel

[Jinky Williams]

Actually, it's been my understanding that it wasn't because they were somehow trying to build their way to heaven, but rather because they were going against the edict of God to go forth into the corners of the world and prosper and instead vying to stay in one place. He then frustrated all communications efforts, not just those associated with building the tower, so that people would congregate with like languages and scuttle off to their own corner.

The God of the Bible would feel not threatened in the least, I think, by humans dorking around and trying to build a heavenscraper.

Re:Warnin', some Cussin' follows.

[Morphine007]

A good way to test this are jokes, because they are such a condensed way of cultural meaning.

Here's another good one: insults/cursewords.

English ones tend to be based around sex; eg. Go fuck yourself. Fuck off you stupid cocksucker, etc...

French ones involve the church and shit; eg. Chrisse de tabarnac osti (a particularly nasty curse phrase... guaranteed to turn heads even amongst rough company, literally translates to "Christ, tabernacle, host") or mange la marde mon osti de chien salle (again, a pretty nasty one... translates to "eat shit you host of a dirty dog"....I've heard it said that you can call a french woman a bitch and she'll hardly bat an eye, but call her a chienne, which is a female dog, ie. a bitch, and she'll fucking go ballistic on you.)

This is another good example of what needs to be overcome. The literal translation of your average swearword/insult from french to english yields a lot of nonsense, most of which isn't offensive at all. If your translator can't even tell when someone is trying to tell you to fuck off before they kill you, then it's probably not worth a salt.

At least it keeps stadiums cool...

[Anonymous Coward]

I am a baseball fan

Je suis un ventilateur de base-ball
Ich bin ein Baseballventilator
Sono un ventilatore di baseball

Good News!

[SirBruce]

It's a suppository!

Bruce

tested using a typical /. post

[mmmmbeer]

When this technology was tested using a typical /. post, the output was "In Soviet Russia, hovercraft's eels are full of you."

Universal translator

[Schraegstrichpunkt]

Farnsworth Sr.: "... and this is my universal translator. Unfortunately so far it only translates into an incomprehensible dead language."

Farnsworth Jr.: "Hello."

Translator: "Bonjour!"

Farnsworth Sr.: "Gibberish!"

Too much spice

[nycroft]

The Bene Gesserit witch must leave!

Translators of Zero Wing contracted...

[ElboRuum]

A few samples from Japanese->English:

"Those walls are several feet thick and can hold back millions of gallons of water..." translated to "High columns having much fat toe plus can carry big number aqua litres"

"I'm not feeling very well, do you have some aspirin?" translated to "This day of my health is in negative. In my possession of you are pills?"

"All of your bases are in our possession." translated to "My tank is fight."

And so on.

toki pona li toki lili

[tepples]

Fine - provided you are willing to be limited to a vocabulary of 100-200 words, according to TFA.

http://www.tokipona.org/

Basic English?

[tepples]

Advocates of Basic English have claimed the following:

• English: 7 years
• Esperanto: 7 months
• Basic English: 7 weeks
• Toki Pona: 7 days

Hype?

[nobelHubel]

While what they are doing is pretty cool, one has to question the utility of the same. You often see the media get all excited about these ideas, when really they aren't really practical. What's the point in translating just words? What kind of half-assed conversation could you have. The point is, if they stick to claiming that they can translate words, it is fine. However, claiming that this will help one have a bilingual conversation is dishonest. They should just turn around and ask the guys working in Machine Translation at LTI@CMU. A horror story or two from there would be a good reality check. :)