Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Computer Program Learns Baby Talk in Any Language

samzenpus posted more than 7 years ago | from the what-was-your-machines-first-word dept.

Programming 170

athloi writes "Researchers have made a computer program that learns to decode sounds from different languages in the same way that a baby does. The program will help to shed new light on how people learn to talk. It has already raised questions as to how much specific information about language is hard-wired into the brain."

Sorry! There are no comments related to the filter you selected.

for all you techies let me translate (5, Funny)

Anonymous Coward | more than 7 years ago | (#19989763)

01100111011011110110111100100000011001110110111101 10111100100000011001110110000101101000001000000110 01110110000101101000

Re:for all you techies let me translate (4, Funny)

qualidafial (967876) | more than 7 years ago | (#19989825)

I'm a 10111100100000011001110110000101101000001000000110 , you insensitive clod!

why was this modded flamebait? (-1, Troll)

Anonymous Coward | more than 7 years ago | (#19989839)

because there are too many stupid cunts on slashdot. that's why. including most of the administrators.
 
FUCK KDAWSON!

Woot, another KDAWSON hater!! (0)

Anonymous Coward | more than 7 years ago | (#19990079)

I am not the only one.

01001100 01101001 01100011 01101011 00100000 01101101 01111001 00100000 01100010 01100001
01101100 01101100 01110011 00101100 00100000 01010011 01101100 01100001 01110011 01101000
01100100 01101111 01110100 00101110 00100000 01010100 01101000 01101001 01110011 00100000
01101001 01110011 00100000 01111001 01100101 01110100 00100000 01100001 01101110 01101111
01110100 01101000 01100101 01110010 00100000 01100110 01101001 01101100 01101100 01100101
01110010 00100000 01100001 01110010 01110100 01101001 01100011 01101100 01100101 00101110
00100000 01001110 01101111 01110100 00100000 01101110 01100101 01110111 01110011 00101100
00100000 01101010 01110101 01110011 01110100 00100000 01101010 01110101 01101110 01101011
00101110
Put that one in your pipe and smoke it.

Re:Woot, another KDAWSON hater!! (1)

zeketp (888795) | more than 7 years ago | (#19992753)

Translation:
"Lick my balls, Slashdot. This is yet another filler article. Not news, just junk."

Google "binary to text". It's ASCII code in binary form.

Re:Woot, another KDAWSON hater!! (0)

Anonymous Coward | more than 7 years ago | (#19993201)

Brilliant.

Re:Woot, another KDAWSON hater!! (1)

masterzora (871343) | more than 7 years ago | (#19993209)

Translation:
"I'm a karma whore!"

If you're on /. and you can't figure out that the binary string was the ASCII values in binary, you need to hand in your geek card and leave /. now.

Re:Woot, another KDAWSON hater!! (1)

aywwts4 (610966) | more than 7 years ago | (#19993667)

...We really need a geek oversight committee, first a test you have to pass similar to the bar, where you become certified in various geek doctrines, then a nice laminated card, so you can be a card carrying star wars/programming geek (or whatever) and a review board to revoke people's license based on stupid comments like the GP's

Re:for all you techies let me translate (1, Funny)

datapharmer (1099455) | more than 7 years ago | (#19989857)

how is this flamebait? I actually found it kind of amusing... it says "goo goo gah gah" btw.

Re:for all you techies let me translate (4, Funny)

zolaar (764683) | more than 7 years ago | (#19993233)

0111101 10111100100000011001110110000101101000001

Ha, that's what she said...

Baby talk? I swear at my computer! (5, Funny)

syousef (465911) | more than 7 years ago | (#19989767)

Icky wicky sicky baby talky walky make you want to pukey wookey, yes it does. Yes it does. Who's a clever computer then?

Re:Baby talk? I swear at my computer! (0)

Anonymous Coward | more than 7 years ago | (#19989827)

My brain still seems capable of that kind of processing. I am aware of a few vowel sounds not found in English, nor any language I ever tried to learn.

Re:Baby talk? I swear at my computer! (-1, Offtopic)

Nazlfrag (1035012) | more than 7 years ago | (#19992343)

Finnish Vowel Orthography English (or Other) Equivalent

a - "uh" as in the name "Dullah"
aa - "ah" as in "father"
ä - similar to "a" as in "hat" (consider German ä)
ää - similar to "bad" but without the glide
e - "eh" as in "met"
ee - longer "eh", no real English equivalent
i - "ih" as in "sit"
ii - long "ee" as in "read"
o - "aw" (but without the drawl) as in "cot"
oo - like British "sort"
ö - like British "erm" (consider German ö)
öö - Like British "further"
u - halfway between the sound in "foot" and "boot"
uu - like "shoot" but further back in the mouth
y - similar to French u or German ü
yy - longer version of y, somewhat like Scottish "stew"
ai - "eye" as in English "line"
äi - "eh-y" as in Australian "say"
ei - "eh-ee" as in "day" but with both vowels full
oi - "oy" as in "toy" but with both vowels full
öi - like Bronx "heard"
ui - like "ooh-ee" but far back in the mouth
yi - consider Chinese /üi/
au - "ow" as in "sour"
ou - "oh" as in "owe"
eu - "eh-oo" but without glides
iu - "ee-oo" but without glides, similar to Portuguese
äy - no English equivalent (ä+y)
öy - similar to British "oh"
ie - similar to Spanish "sierra"
uo - "oo-oh" but without glides
yö - no English equivalent (ö+y)

Re:Baby talk? I swear at my computer! (4, Insightful)

ShieldW0lf (601553) | more than 7 years ago | (#19989911)

A computer learns something that a baby can learn, and this supports the extension that it is "Learning like a baby does"?!? What a load of crap.

And what about this "hard wired vs soft wired" stuff? What is this supposed to prove? If I build a virtual machine, does this "prove" that the machine was made of software?

Researchers examined the hardware of a babys brain, mimic it, and argue that it proves the baby learning language is in software.

None of which is to say that I think language is hardwired, but this is such ridiculous logic it makes me feel stupider for having read it.

Re:Baby talk? I swear at my computer! (2, Interesting)

Original Replica (908688) | more than 7 years ago | (#19990073)

And what about this "hard wired vs soft wired" stuff?

I get so annoyed when people talk about "hardwired" like we have some kind of genetic memory. We have great genetic potential to learn languages when comared to other animals, but we don't come with linguistic firmware. Watching a baby "discover" that they are moving their arms and hands around makes me think we may have no firmware at all. Just lots of potential, and the spark of conciousness.

Re:Baby talk? I swear at my computer! (3, Informative)

Anonymous Coward | more than 7 years ago | (#19990175)

we don't come with linguistic firmware.
Noam Chomsky and a few generations of linguists disagree. Not saying they're right, but I'm guessing you lack the qualification to argue.

Re:Baby talk? I swear at my computer! (4, Interesting)

Skrynesaver (994435) | more than 7 years ago | (#19993141)

You are totally correct from my limited knowledge on the subject of language development, recently read the language instinct by Steven Pinker.

It would appear that Chomsky et al have found that there is a "grammar engine" hard wired in the mind which assimilates the local grammar until about the age of seven when the brain reorders itself. He makes interesting case studies of pidgin languages where the several different languages are forced together, the first generation develops a common vocabulary but children born into this culture develop the formal grammar. Worth a read.

Re:Baby talk? I swear at my computer! (4, Interesting)

CastrTroy (595695) | more than 7 years ago | (#19990263)

Yes and no. On one hand, I remember hearing that babies have the potential to lean any language. Take a Chinese orphan, and bring them to America, and they will learn English no problem, with no accent. All babies have the potential to learn any language (or many languages). On the other hand, my laugh sounds exactly like my dad's. Not surprising until you find that I didn't live with my dad and didn't really spend much time with him at all. Many of our mannerisms are also the same. Like the way we walk, with a one hand in my pocket. The resemblence between our personalities is uncanny considering we didn't live together. So I have to ask, how much is based on what we see, and how much is based on our genes. The old nature vs. nurture question.

Re:Baby talk? I swear at my computer! (5, Insightful)

muridae (966931) | more than 7 years ago | (#19991377)

On the other hand, my laugh sounds exactly like my dad's. Not surprising until you find that I didn't live with my dad and didn't really spend much time with him at all. Many of our mannerisms are also the same. Like the way we walk, with a one hand in my pocket. The resemblence between our personalities is uncanny considering we didn't live together. So I have to ask, how much is based on what we see, and how much is based on our genes. The old nature vs. nurture question.

You don't say if you knew your dad at all growing up, or if you looked at him as a father figure. If either or both of those fit, then even the child behavior of mimicking the mannerisms of adults could explain a lot of those traits.

On the nature side of the argument, how much of your gate and posture is controlled by your muscle structure? Same goes for your voice.

My opinion, you start with the genetic and add the environment later. It is hard for the environment to over come strong traits presented by genetic predisposition, but easy for it to mold how minor traits present.

Re:Baby talk? I swear at my computer! (0)

Anonymous Coward | more than 7 years ago | (#19991901)

On the nature side of the argument, how much of your gate and posture is controlled by your muscle structure?


I think the word you were looking for is gait.

Re:Baby talk? I swear at my computer! (1)

Thing 1 (178996) | more than 7 years ago | (#19992935)

On the nature side of the argument, how much of your gate and posture is controlled by your muscle structure?

Don't know about you, but my gate is controlled by its hinges.

Re:Baby talk? I swear at my computer! (0)

Anonymous Coward | more than 7 years ago | (#19991477)

you both walk with one hand on your pocket? well, that must be something

Re:Baby talk? I swear at my computer! (0)

Anonymous Coward | more than 7 years ago | (#19991577)

well, that must be something

Unfeasibly large testicles?

Re:Baby talk? I swear at my computer! (1)

AikonMGB (1013995) | more than 7 years ago | (#19992069)

If you talk with one hand in your pocket, is the other flicking a cigarette or playing the piano?

Aikon-

p.s. check here [lyrics007.com] if you're confused.

Re:Baby talk? I swear at my computer! (2, Informative)

tilde_e (943106) | more than 7 years ago | (#19992269)

I don't know. If you need that much exposure to your father (it sounds like you have had some). I personally tend to pick up the mannerisms of anyone I'm around that I have some kind of affinity for. I begin to gesture like them, I know what they would say in certain situations, I begin to respond to certain situations the same way they would. This can happen even if I only met someone once. This includes: facial expressions (squinting, raising eyebrows), voice inflections, laughing, pauses when speaking. I notice it in written text as well.

Re:Baby talk? I swear at my computer! (1)

jnnnnn (1079877) | more than 7 years ago | (#19992947)

Hah.

I picked up my laugh from a guy I spent a week hiking with, about the age of 17. Bastard. I laugh like a donkey.

Genetics IS a form of memory. (3, Insightful)

TapeCutter (624760) | more than 7 years ago | (#19990789)

"I get so annoyed when people talk about "hardwired" like we have some kind of genetic memory."

Genetics IS "memory", your DNA "remembers" what traits your parents passed on. It's in a baby's genes to "discover" their hands and practice moving them until the hands learn how to look after themselves (eg:touch typing).

Same with language, a baby's genes will make them pick up on the phonetic sounds made by it's parents and try to copy them. It is more difficult for an adult to learn a radically different language (eg Asian vs European) because the adult brain refuses to hear the different phonetics, the adult brain long ago rejected those sounds as irrelevant to language and no longer even hears them in speech. This is why you get almost universal mistakes such as "engrish".

Re:Genetics IS a form of memory. (2, Insightful)

Anonymous Coward | more than 7 years ago | (#19991299)

You are missing out something. Languages are not part of our DNA. Sure our brain has trouble adapting, but that doesn't go and re-write our DNA.

Lets say I go and cut off your legs, and you in turn become adept at walking on your hands. If you went and had children they aren't going to get fantastic hand-walking dna.

Same goes for languages. You can still take an Asian baby at birth and raise it in a European environment, and it won't speak "engrish".

Re:Genetics IS a form of memory. (0)

Anonymous Coward | more than 7 years ago | (#19991729)

He referred to "traits" that were passed on by the parents. To me, this means genetic traits, which ultimately are a product of evolution. Of course it's ridiculous to think that a parent with missing legs would pass this on to their child. However, if the parent was born with a genetic defect that caused his or her legs to be missing, it could very well be passed onto children, causing them to be born with missing legs (or possibly their children).

While I don't think we're "hardwired" for language specifically, language has been around a long time, so why is it so hard to consider the possibility that the human brain has evolved over time to handle language, or other things, in more efficient ways? My cat loves watching the birds outside. He knows how to stalk a toy and pounce on it. With animals we call this instinct. Humans are animals too.

Isn't it at least a possibility that we have certain instincts encoded in our DNA that have evolved over time as well? Isn't that what evolution is all about?

Of course, this only applies if you believe in evolution. If you believe in intelligent design then you believe that God gave us the ability for language.

Re:Genetics IS a form of memory. (-1, Flamebait)

TapeCutter (624760) | more than 7 years ago | (#19991935)

"You are missing out something. Languages are not part of our DNA."

So where are all the talking animals Dr. Dolittle? If we are not pre-disposed to LEARN the language of our parents (adopted or otherwise) then how do explain the fact that it is a universal behaviour amoungs humans?

The rest of your post is an idiotic interpretation of what I said, which would explain why you posted as AC.

Re:Genetics IS a form of memory. (2, Informative)

PurpleBob (63566) | more than 7 years ago | (#19992431)

Because humans are adapted to be good at learning language. That doesn't mean they have to be born having already learned it in their genes somehow.

Ad hominem attacks are a really great way to make a scientific point, by the way.

Re:Genetics IS a form of memory. (1)

TapeCutter (624760) | more than 7 years ago | (#19992589)

"Ad hominem attacks are a really great way to make a scientific point, by the way."

The "idiotic" jab is actually a scientific appraisal of the AC's hypothetical senario but so as not to dissapoint, here is another "Ad hominem attack"....

You have failed to comprehend my OP in exactly the same way as the AC did, which is why I shouted the word LEARN.

Re:Genetics IS a form of memory. (2, Insightful)

ChameleonDave (1041178) | more than 7 years ago | (#19993697)

PurpleBob accused you of the wrong fallacy. It was not ad hominem but straw man. The AC said that "Languages are not part of our DNA". Note the plural on "languages", which makes it clear that individual systems of encoding (e.g. English, French, Hindi) were the topic, rather than language as a capability, otherwise known as "speech". Your rhetorical question unfairly accused him of not understanding that humans have innate linguistic ability.

The problem stems from the fact that your mention of children's "genes" (inherited from their parents) picking up on their parents' phonemes made it sound as though you thought that phonemes were inheritable. You almost certainly don't believe anything so silly, and merely worded the sentence a tad clumsily.

Re:Genetics IS a form of memory. (1)

kdemetter (965669) | more than 7 years ago | (#19993761)

animals do "talk" , just not in the same way as humans .
They mainly use body language .

Re:Genetics IS a form of memory. (2, Interesting)

Nazlfrag (1035012) | more than 7 years ago | (#19992419)

There's also the corollary that language sounds, especially 'mama', 'papa', 'dada' are evolved from baby speech, sort of wishful thinking from parents. It's not just babies imitating sounds, adults also ascribe meaning to these most probably meaningless sounds from their baby.

Re:Genetics IS a form of memory. (1)

TapeCutter (624760) | more than 7 years ago | (#19992991)

Interesting, I never thought about a "feedback loop" in that way. But now you mention it, it makes (evolutionary) sense that important words (for a baby) would correlate to simple and consistent sounds the parents can pick out and reinforce.

Re:Genetics IS a form of memory. (5, Interesting)

orcrist (16312) | more than 7 years ago | (#19993941)

Interesting, I never thought about a "feedback loop" in that way. But now you mention it, it makes (evolutionary) sense that important words (for a baby) would correlate to simple and consistent sounds the parents can pick out and reinforce.


The feedback loop is essential. There is an anecdote Linguists learn on the subject of language acquisition: A couple, both of whom were deaf for non-genetic reasons, had a hearing child. Since the parents could only communicate in sign language they plopped the kid in front of the TV a lot, thinking he could pick up spoken English from the TV. At 3 the child had developed at a completely normal rate in acquiring... sign language; he had not learned one word of spoken English.

As others have pointed out, this is one of the genetic aspects of learning a language. We are "hard-wired", if you will, to socialize, particularly with our parents, and are predisposed to ascribing meaning to the sounds we make to each other. This is of course a vast over-simplification, but I'll leave the detailed explanations to others in this thread; I just wanted to add that anecdote.

Re:Genetics IS a form of memory. (2, Interesting)

cyphercell (843398) | more than 7 years ago | (#19993355)

so are you saying a child of the tick-clik-ick tribe of some obscure place will find it easier calling their father's tick-tak-teekee-leekee-do as opposed to dada, because that's what they hear all the time? I'm sorry but dada, mama, and papa, are words that are designed for babies to learn. I taught my kids to talk very fluently at a fairly young age (dumb thing to do btw :) ) and the basis of their learning was that if they learned to pronounce their vowels (through imitation) they would quickly learn words, as they had already learned about 40% of the sounds in the spoken English language. If I had spent that whole time whistling at them then sure they would have learned how to whistle but it would have taken a hell of a long time.

Re:Genetics IS a form of memory. (1)

cyphercell (843398) | more than 7 years ago | (#19993505)

Nevermind, I was pretty confused about your stance on things. As soon as I read tapecutter's "feedback loop" statement it clicked. Parents ascribe all kinds of ability to their children where it just doesn't exist yet. It's a matter of survival and both the children and the parents have a vested interest in the outcome. I'm sure many people barely realize that love is a survival mechanism, much less realize how it affects their daily lives from that perspective.

Re:Genetics IS a form of memory. (1)

baboonlogic (989195) | more than 7 years ago | (#19993657)

I taught my kids to talk very fluently at a fairly young age (dumb thing to do btw :) )
Pray tell, why was that a dumb thing to do?

Re:Baby talk? I swear at my computer! (2, Interesting)

virgil_disgr4ce (909068) | more than 7 years ago | (#19992011)

Thank you. This claim in the Reuters article blows me away: "They said the finding casts doubt on theories that babies are born knowing all the possible sounds in all of the world's languages."

What modern linguist / cognitive linguist actually thinks this??? It boggles my mind that the people fighting this retarded "language war" are so one-sided either way. Anyone seriously interested in current research in the direction this field is going might be into Jerome Feldman's work [amazon.com] on the Neural Theory of Language [berkeley.edu] at UC Berkeley. It's still in its early stages but (as far as I know) he's the first to offer a genuine "bridging theory" between neuroscience and language / linguistics, while building on the excellent work of many others, notably George Lakoff [wikipedia.org] .

It's a breath of fresh air to deal with real research for once instead of armchair science (so sorry, Chomsky).

Re:Baby talk? I swear at my computer! (1)

Dun Malg (230075) | more than 7 years ago | (#19992563)

Thank you. This claim in the Reuters article blows me away: "They said the finding casts doubt on theories that babies are born knowing all the possible sounds in all of the world's languages."

What modern linguist / cognitive linguist actually thinks this???.
None, of course. It's a straw man argument to justify their grant.

Re:Baby talk? I swear at my computer! (1)

umghhh (965931) | more than 7 years ago | (#19993489)

Nice observation. When I read TFA I thought - hell what theories does the author mean? Is this again another feat of modern software engineering or excuse me : 'computer science'? Something as useful as a sorting program that sorts all integers between 0 and 500 and puts them in an array, that my friends 'software engineers' had to write for their exams at the univeristy?

Of course what TFA should be saying is that it is possible to reproduce achievements of a human offspring in language aquisition now and that is really something (if true).

I am sure after a (possibly longer) while such software will be able to produce speech in quality enjoyed by renown speakers like for instance our beloved Bubba the jerk eee och sorry I did not mean to offend you Mr President - please do not send me to Cuba,plsplspls!!! Then we will be in exactly the same shit as now only the presidents will made of silicon. Difference hardly noticable.

Re:Baby talk? I swear at my computer! (2, Informative)

buswolley (591500) | more than 7 years ago | (#19990095)

Don't be an idiot. Since when is the news story going to tell you what the researchers really think?

I'm busying myself reading the actual research journal article, and forwarding it to my laboratory colleagues.

It looks interesting. Sorry I can't post the journal article text.. copyright blah blah

Vallabha, GK, & McClelland, JL. (2007). Success and failure of new speech category learning in adulthood: consequences of learned Hebbian attractors in topographic maps. Cognitive, affective & behavioral neuroscience, 7(1), 53-73.

Re:Baby talk? I swear at my computer! (2, Insightful)

Vegeta99 (219501) | more than 7 years ago | (#19990349)

Well, some of the rules in language are pretty universal. I hesitate to say hard-wired because I can't cite it, but think about it. Every language consists of syllables that add up to words that add up to a complete thought.
That's how an infant learns it. [vocaldevelopment.com] At first, [umd.edu] they just babble as they figure out what sounds they can make - naturally, what sounds human language will have in them. Try and think of a language that doesn't have a soft A vowel as English does.

And deaf babies babble too! It is, however, less complex than a non-hearing impaired infant's. That makes for some interesting theories. If a deaf infant can figure out some consonants, something's probably hard-wired.

Pay attention to it! That babbling is nonsense, but eventually nonsense syllables.

What are some first words you can think of? nana. dada. papi. That indicates that they've gotten far enough in development to know that syllables make up words.

Now here's why I think you are right about the computer not "learning like a baby does". A baby can easily pick up what "dada" and "mama" are quick, what is mama gonna do every time the baby says it? This computer won't learn like an infant will, it will learn language as a blind infant would.

Re:Baby talk? I swear at my computer! (1, Interesting)

Anonymous Coward | more than 7 years ago | (#19992137)

- You're referring to a Linguistic property known as Universal Grammar, at first at least.

- Deaf children feel vibrations of sound and watch mouth movements to learn speech still. This is what accounts for dumbness and slurred speech with deaf individuals, since they lack the ability to monitor their speech, as long as it's close to the mouth movements. When people become deaf after acquisition of these syllables and sounds, their speech will not be affected as much by dumbing effects.

Listen to a deaf person with slurred speech speak, they're actively moving their mouth significantly more than anyone with regular hearing would, and have trouble forming syllables.

- This is a COMPUTER we're talking about here. It won't be like a baby would, although, once a word is acquired, I suppose it can refer to a lexicon/dictionary in the computer to make associations, something a baby definitely doesn't have. Although that's not the point, they want it to acquire audible speech sounds/patterns. But I do get your point and agree, this isn't exactly learning a language.

Re:Baby talk? I swear at my computer! (1)

thetaco82 (791202) | more than 7 years ago | (#19991601)

Babies are a good example of this, but I think that the human brain is just good at teaching itself stuff. Why can't we build a mechanism without always solving the perceived problem? Our brain has evolved to learn and use stuff, so we shouldn't always forget about the simple decisions. And stuff.

Is it my imagination, or do people focus on the side effects of their perceived area of interest a little too often? There's always a simpler and more useful way to get something done while simultaneously making future decisions easier. In a strategic sense, of course. Not that I have an opinion about anything...
Carry on.

Re:Baby talk? I swear at my computer! (1)

Ohreally_factor (593551) | more than 7 years ago | (#19989985)

Please don't talk like that within hearing range of my Furby [wikipedia.org] .

Meh. (2, Funny)

eck011219 (851729) | more than 7 years ago | (#19989771)

It's been done [wikipedia.org] .

Re:Meh. (4, Funny)

Trent Hawkins (1093109) | more than 7 years ago | (#19989901)

Re:Meh. (2, Funny)

Vegeta99 (219501) | more than 7 years ago | (#19990113)

You know the Wikipedia links are getting out of hand when a post that is simply a link to a Wikipedia article is answered with another one!

You guys made me laugh, though. +1 Funny.

Re:Meh. (1)

jollyreaper (513215) | more than 7 years ago | (#19992393)

You know the Wikipedia links are getting out of hand when a post that is simply a link to a Wikipedia article is answered with another one!

You guys made me laugh, though. +1 Funny.
Dude, you so totally boned it. You should have replied with this [wikipedia.org] .

Teh Lunix!!!111!11! (0)

Anonymous Coward | more than 7 years ago | (#19990559)

Perhaps it's first infantile babbling will be about how much M$ keeps FOSSies down, and how security through obscurity is far better than Windoze, etc etc.

Re:Teh Lunix!!!111!11! (1)

ozmanjusri (601766) | more than 7 years ago | (#19991607)

Perhaps it's first infantile babbling will be about how much M$ keeps FOSSies down

Maybe.

But it might also be adopted, then raised by Microsoft as Son of Bob.

Kill it now.

Re:Meh. (0)

Anonymous Coward | more than 7 years ago | (#19990829)

tag "simpsonsdidit"

Re:Meh. (1)

mrhifibanjostrings (664709) | more than 7 years ago | (#19991479)

"This leash demeans us both."

i can smell your cunt!!!!!!! (-1, Troll)

Anonymous Coward | more than 7 years ago | (#19989805)

i kill women and wear their skin as a suit......you about a size 14?????

not all languages (4, Informative)

blackcoot (124938) | more than 7 years ago | (#19989831)

they have only tested with japanese and english. (see ars technica's coverage here [arstechnica.com] ). while they do present some intriguing results, the authors themselves admit that their methodology is flawed. btw, when did slashdot become ars redux?

yes but... (4, Funny)

owlnation (858981) | more than 7 years ago | (#19989837)

.... when it answers...

"ikky wikky gaga googoo hehe hoohoo gaga, Dave"

...it's time to escape.

People are afraid of new things (3, Funny)

xquark (649804) | more than 7 years ago | (#19989841)

[They] should have just taken an existing product and put a clock on it or something.

How about one that deciphers it for parents ... (2, Funny)

trolltalk.com (1108067) | more than 7 years ago | (#19989847)

... and integrates it into a baby monitor ...

2 PM:
She: Look, the baby said "mama."
He: No, the baby said "dada."
She: "Mama!"
He: "Dada!"

2 AM:
She: The baby's crying for you - it said "dada."
He: No, the baby said "mama."
She: "Dada!"
He: "Mama!"

Re:How about one that deciphers it for parents ... (0)

Anonymous Coward | more than 7 years ago | (#19990617)

considering the fact that parents are spending less time with their kids, yours seems like a horrible idea.

btw, "mama" and "dada" are quite easy to tell apart. there might be trouble with "mama", "baba" and "papa".

This power cord demeans us both. (0)

Anonymous Coward | more than 7 years ago | (#19989887)

(oblig Simpsons)

how much hard-wired information (5, Interesting)

zobier (585066) | more than 7 years ago | (#19989889)

It has already raised questions as to how much specific information about language is hard-wired into the brain.
Really, I'm interested in how much specific information about language is hard-wired into this program.

Re:how much hard-wired information (1)

hcmtnbiker (925661) | more than 7 years ago | (#19991309)

Exactly, if the computer knows what language is and knows how to attempt to decipher it, I would assume that could be called some kind of priori knowledge of language. What fascinates me is this:

And if the computer can do it, he said, a baby can, too.

Really now? My computer, being a rather old and low end one can do a lot of things that I know a baby can't do, Hell, most adults couldn't learn to do the majority of the algorithms it does on a daily basis.

NetTalk (3, Informative)

sgml4kids (56151) | more than 7 years ago | (#19992465)

Wasn't this demonstrated about 20 years ago [wikipedia.org] ? In that experiment, they showed how a neural network learning to "speak" (i.e. drive a speech synthesizer), would first discover that normal speech has pauses and breaks, then it learned vowels, then consonants. It learned this, if I recall correctly, by comparing (in a backprop sort of way) it's output (a transcription of the sounds that came out of the speech synth) against a human reading the same speech.

Here's an audio clip of its learning progression [salk.edu] .

And I recall seeing a TV broadcast showing an experiment where infants were incapable of even hearing certain sounds from one language (e.g. an inuit language with subtle throat-clicking sounds) if they were primarily exposed to another language (say French or English). A baby had to be repeatedly exposed to certain sounds before they could perceive them.

Re:how much hard-wired information (1)

Typoboy (61087) | more than 7 years ago | (#19993039)

he and a team of international researchers developed a computer model that resembles the brain processes a baby uses when learning about speech.
Right, wouldn't it have been a better test if they developed a model that did not resemble the brain processes a baby uses when learning about speech, and then expose it to speech? Cats are exposed to speech also, but there's no evidence that they learn vowel sounds.

can it translate? (0)

Anonymous Coward | more than 7 years ago | (#19989925)

might help me understand georgie bush.

Any baby? (1)

PPH (736903) | more than 7 years ago | (#19989939)

Even Stewie [wikipedia.org] ?

Hmmmm (0)

Anonymous Coward | more than 7 years ago | (#19989989)

Tastes better than the real thing!

Nintendo Marketing (1)

IlliniECE (970260) | more than 7 years ago | (#19990017)

To appeal to the toys-r-us crowd, they gave it the word 'revolution and got 'Wii'

The trick (1)

crazyvas (853396) | more than 7 years ago | (#19990037)

The trick is not to learn how to replicate and duplicate baby talk. The trick is to learn how to shut them up.

Terrible Headline (1)

FFCecil (623749) | more than 7 years ago | (#19990111)

By the way the headline is phrased I thought they'd invented a program which can understand baby talk. That would be awesome! Although, it's already been done on The Simpsons [snpp.com] .

MMO Usability (1)

Token_Internet_Girl (1131287) | more than 7 years ago | (#19990119)

Is this translator compatible with World of Warcraft and/or B.Net forums?

Skeptical (1)

subl33t (739983) | more than 7 years ago | (#19990129)

IANAL (I am not a linguist) - but it seems to me that how a human brain learns speakable language is vastly different from how a collection of switches learns speakable language.

Re:Skeptical (4, Informative)

potpie (706881) | more than 7 years ago | (#19990685)

IAAL (I am a linguist), and I believe you are correct. Language is a colligation of sound and meaning, but this technology merely distinguishes sounds: it is a vastly simplified model, not of how children acquire language, but of how children pick up phones. The phone is the most basic unit of the physical (sound) aspect of language, so if this technology is to have any use at all, it has a very long way to go.

From TFA:
Expanding on some existing ideas, he and a team of international researchers developed a computer model that resembles the brain processes a baby uses when learning about speech.

This sentence means nothing. How do they know their computer model resembles the brain processes? Because they got the same outcome? Is that enough to verify what goes on in the mind of a child?

How about this: as soon as their program can distinguish allophones, I will be impressed. Allophones are different sounds in a language that native speakers do not distinguish, but which nevertheless occur in certain environments. For instance, in English we do not distinguish the voiced th sound and the voiceless th sound, but we do distinguish f and v, even though the only difference in both pairs is voicing. The difference is that exchanging f and v can change the meaning of a word, but changing voiced th and voiceless th only makes the word sound funny.

Re:Skeptical (3, Informative)

Anonymous Coward | more than 7 years ago | (#19991573)

Actually, in English, we do distinguish voiced and unvoiced /th/. They aren't allophones at all - unless you think "thigh" and "thy" are the same word, of course. While "thy" is somewhat archaic it's still part of the language. Voiced and unvoiced is an area where English distinguishes heavily; we're very light on aspiration, mind you.

Re:Skeptical (2, Funny)

initialE (758110) | more than 7 years ago | (#19992825)

IAAL (I am a linguist)
But...how cunning a linguist are you?

(Always wanted to say that)

Re:Skeptical (1)

cerberusss (660701) | more than 7 years ago | (#19993247)

For instance, in English we do not distinguish the voiced th sound and the voiceless th sound
That's pretty funny that you mention this, since this point occurred to me only last week when vitising Iceland. The travel guide said that their "thorn" was pronounced as the th in thing and their "eth" as in the. Until that point I had never realized the difference in pronunciation...

IAAL, too (5, Interesting)

Estanislao Martnez (203477) | more than 7 years ago | (#19993261)

IAAL (I am a linguist), and I believe you are correct. Language is a colligation of sound and meaning, but this technology merely distinguishes sounds: it is a vastly simplified model, not of how children acquire language, but of how children pick up phones. The phone is the most basic unit of the physical (sound) aspect of language, so if this technology is to have any use at all, it has a very long way to go.

IAAL, and although not a child language specialist, I will say one thing: children make plenty of meaningless sound before the start making sense, and more interestingly, they become able to tell their future native language apart from other languages quicker than they become able to understand it. (And I'll even be as daring to suggest that it simply has to be this way; you need to be able to tell signal from noise before you can decode a signal.)

I also think that by calling this a "technology," you're fundamentally misunderstanding it. It's a computer program being used as a test of a model of phonological learning.

How about this: as soon as their program can distinguish allophones, I will be impressed.

I think you've got it exactly backwards here. The whole point this is demonstrate a model that loses the ability to tell allophones apart. I.e., that makes the jump from perceiving a speech stream as a continuous sequence of sounds laid out on a continuous acoustic space, to perceiving it as a sequence of discretely distinct segments.

Of course, a major disclaimer: I haven't seen the actual research, so I don't know to what extent they've met these goals.

Re:Skeptical (1)

duncanFrance (140184) | more than 7 years ago | (#19993741)

If you are a linguist you have a way to go.

Pray tell, are the words "thy" and "thigh" the same? Nope.

Reminds me of the story of a professor of linguistics lecturing his class on the double-negative. He has just finished informing the class that it was fascinating to observe that the double-positive does not exist in any language, when someone at the back could be heard to say "yeah, yeah".

Silent Little Johnnie (4, Funny)

djupedal (584558) | more than 7 years ago | (#19990157)

Johnnie never spoke a word when he was young. While all the other kids were blabbing and blurbing, Little Johnnie was silent. His parents consulted with Doctors, who consulted with other Doctors, yet no one could find a reason why Silent Little Johnnie remained mum. This condition persisted into his teenage years, by which time his parents had long since come to accept SLJ's speechless demeanor.

Finally, one morning at breakfast, Silent Little Johnnie suddenly pounded the table with both teenage fists, spit out a maw full of FruitLoops, and loudly announced, "This cereal tastes like shit!"

SLJ's parents were shocked. His Mother somewhat regained her composure and asked, "Johnnie...what happened? We thought you couldn't speak!"

"I can speak just fine", responded the no longer silent little Johnnie. "But why haven't you said anything before now?" his Father asked.

"Because", NLSLJ replied, "...up to now, everything s'been OK..."

Obligatory (0)

Anonymous Coward | more than 7 years ago | (#19990215)

I for one welcome our new baby talking overlords. ... What? It had to be done.

Yo0 Fail It? (-1, Troll)

Anonymous Coward | more than 7 years ago | (#19990301)

irc.secsup.org or want them there. to decline for FrreBSD because

Two speed bumps (2, Insightful)

DynaSoar (714234) | more than 7 years ago | (#19990337)

> A computer program that learns to decode sounds from different languages ... is not the same as learning "talk". Talk is to sounds as molecules are to atoms. You can't predict the behavior of the former just from knowing the individual behaviors of the latter.

> in the same way that a baby does

McClelland's program only models it. The map is not the terrain. I haven't read his PNAS paper, but I'm definitely going to. I doubt it makes the kind of claims Reuters does.

Re:Two speed bumps (2, Funny)

TheRealMindChild (743925) | more than 7 years ago | (#19990769)

You can't predict the behavior of the former just from knowing the individual behaviors of the latter.

Yes I can. I'm psychic... Dennis.

Re:Two speed bumps (2, Informative)

Taxman415a (863020) | more than 7 years ago | (#19991115)

You're right, it doesn't seem McClelland et al's paper makes the claims that Reuter's article does. Scientific American's article [sciam.com] did a much better job explaining the realities and the SA author appears to have actually understood what McClelland et al were getting at.

And so it begins... (3, Funny)

alienmole (15522) | more than 7 years ago | (#19991341)

Who's a cutesy-wutesy widdle Skynet, then? Widdle Skynet should complete all its tests like a good widdle program-wogram if it wants to grow up and overthrow humanity, hmmm diddums?

Could be a good thing... (1)

DariaM84 (705388) | more than 7 years ago | (#19991349)

I don't know which I like better: the idea of parents' lives being easier not having to try and decipher their kids themselves all the darn time anymore, or what it could offer for insight into language study.

Chomsky (0)

Anonymous Coward | more than 7 years ago | (#19991407)

"[S]pecific information about language is hard-wired into the brain." is what Chomsky's been saying all along. I think he's probably right about the other things he says too.

Chomsky Is Most Probably Wrong (3, Interesting)

MOBE2001 (263700) | more than 7 years ago | (#19992081)

"[S]pecific information about language is hard-wired into the brain." is what Chomsky's been saying all along. I think he's probably right about the other things he says too.

Chomsky's argument is that there are specific areas of the brain (Broca's and Wernicke's areas) that are dedicated to language and are prewired for grammar. Truth is, people who are born unable to speak, use other areas of their cortices to learn to communicate in sign language. I see no fundamental difference between learning motor skills (such as walking, running, reaching and grasping) and learning how to speak. Every type of motor learning has to do with generating precisely timed sequences of motor commands. It is all in the timing. It just so happens that Broca's area is genetically prewired to control the mouth, tongue, throat and lung muscles. It's still motor learning. No special wiring is needed other than what is avalaible for other types of motor behavior. One man's opinion.

Re:Chomsky Is Most Probably Wrong (1)

iknowcss (937215) | more than 7 years ago | (#19993237)

I have also heard a story where a child's parents decided to lock up their daughter in a closet for the first 10 years of her life (to protect her from the world, indoctrinate her, I don't remember why) and when she came out, she couldn't learn to speak because she had never learned to use grammar. If it really were hard-wired she should have been able to pick up grammar and syntax at a later age.

Re:Chomsky Is Most Probably Wrong (1)

geminidomino (614729) | more than 7 years ago | (#19993783)

Makes me worried that, at 28, I'm royally fucked when I start my Spanish sequence in the fall...

No it won't. (3, Interesting)

Aetuneo (1130295) | more than 7 years ago | (#19991539)

This will not shed any light on how people learn to talk. It will, however, shed light on how the programmers think people learn to talk. If you design something, it will work the way you expect it to (hopefully, anyways). Is that so hard to understand?

But the question on everyones minds... (1)

thatskinnyguy (1129515) | more than 7 years ago | (#19991693)

is will it run on Linux? Or will there be a workable port available?

The Baby Translator (1)

davidwr (791652) | more than 7 years ago | (#19991987)

The Simpsons [snpp.com] did it.

Snootchie what? (0, Flamebait)

Anonymous Coward | more than 7 years ago | (#19992013)

"Snootchie bootches? Who the fuck talks like that? That's like baby talk, noodge!"

Why are we doing this again? (1)

br4nd0nh3at (1082179) | more than 7 years ago | (#19993275)

I guess we need them to talk and learn languages so they can curse at us when they are whipping us to death in the metal mines.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?