Wednesday, December 14, 2005

The Problem With Meaning

A few years ago, during one of my rabid "embodiment" phases, I sat in on an AI discussion group comprised mostly of people who actually worked on AI. Being a mere cognitive psychologist, without a much knowledge about computers, I learned a lot, though I think most of the points and questions I raised were pretty stupid (I imagine some of the people in the group cringed every time I opened my mouth). However, there was one problem that I noticed when the AI people talked about "meaning," and no one in the group gave me what I felt was a satisfactory answer to it, so it's bugged me off and on ever since. The way I saw the problem back then was that in certain cases, it's necessary to understand the affordances of objects in order to understand sentences, and understanding affordances requires having a body. I'm no longer so certain that you need a body to understand the affordances of objects, but what you would need in place of that would be such a large body of interconnected knowledge, along with a wealth of "theories" about how to use that knowledge, that building an artificial system capable of comprehending some very simple sentences would be near impossible.

To illustrate this problem, consider two sentences.
(1) John kicked the ball to Mary.
(2) John crutched the ball to Mary.
The syntactic structures are the same, and it would be easy to teach the syntax to a computer. Thus you could get the machine to understand the outcome of the event described in the sentence: Mary ends up with the ball, as a result of an action performed by John. But what if you asked the machine to describe how John got the ball to Mary? What if the computer's task was to describe John's action? It could probably do OK with sentence (1), because the action isn't a novel one, and having been programmed with the meaning of the word "kicked," all it would have to do is spit that meaning out. But sentence (2) contains a novel verb, one which the machine is unlikely to have in its lexicon (unless the programmer has read the paper from which I stole the verb, and is trying to get one past me). You and I shouldn't have much trouble figuring out John's action in (2), even without context (if we added a little context, such as a sentence preceding both (1) and (2) that read, "John was standing across the table from Mary, and the ball was on the table," figuring out (2) would be even easier for us). What would the computer need to describe John's action in (2)?

The answer is that the computer would have to understand what sorts of actions are possible with a crutch -- the affordances of crutches -- as well as being able to reason about which of those actions would be effective in performing the action described in the sentence. As I said, I used to think that this required having a body (because affordances are organism-specific, and even body-specific), and that may still be the case. But if it doesn't require having a body, and even if it does, you've got to have a whole heck of a lot of background knowledge and folk theories to get the affordances of a crutch for John, and pick the relevant ones for a given context. For example, you'd have to know that the hard end of a crutch can be used to apply force to other solid objects (i.e., to push them); you'd have to know that balls are generally light enough to be pushed by a crutch; you'd have to know that some ways of applying force will work in some situations, but not in others (e.g., John and Mary may be close to each other, or indoors, making swinging the crutch like a baseball bat to hit the ball over to Mary impractical, and even dangerous); if you knew that the ball was far enough away from John that he would be forced to fully extend his arm and utilize the full length of the crutch to get to the ball, you'd have to know that the mechanics of the situation would probably require John to hold onto the bottom of the crutch and use the top (the part that goes under your arm when walking with a crutch) to hit the ball, while if the ball were closer to John, it might be easier to use the crutch the other way around. The list of things could go on and on. And the machine would have to know things like this for every novel verb it came across (and novel verbs, particularly denominal verbs like "crutched," are pretty common in everyday language).

So that's the problem I saw back then, and still see today. In order to write a program that can understand the meaning of sentences with which you and I would have no trouble, you basically have to program in most or all of the knowledge of at least a well-developed human child, if not an adult. And I don't see how that's really possible. It certainly doesn't seem to be possible today, since we don't have a firm understanding of how people reason about the mechanics of situations like the one in (2), or how they activate the relevant background knowledge (the paper linked above gives one potential answer, in the form of the "Indexical Hypothesis"). If a machine doesn't have that level of knowledge, every time it gets a novel verb, it's going to be lost.

38 comments:

Speedkill said...

That point was made in the undergrad AI class I just took. The problem with a program understanding, say, a sentence, isn't parsing it out, but storing all the background knowledge we take for granted. Which of course leads to much amusement when playing with the chatbots on the web or reading transcripts of the Loebner Prize competition.

Anonymous said...

In order to write a program that can understand the meaning of sentences with which you and I would have no trouble, you basically have to program in most or all of the knowledge of at least a well-developed human child, if not an adult. And I don't see how that's really possible.

Of course this is not possible.
But this is the wrong approach and this is why you are doomed just like all AI researchers in the last 50 years!
Can you see where and how you err?

1) You assume to think/speak on behalf of a "perfect" listener who will always "get it right", neither you, me or anyone else does that, we do have lots of misundertanding and still succeed in communicating nonetheless.
2) You unconsciously assume some kind of "design" about the required internals of a speech understanding software. There must be "somewhere" some definition of the meaning of words and the software will have to "retrieve" those meanings and accordingly...
And "accordingly" what?

You just started building some prototype architecture without giving any thoughts about what you are actually doing and going with all those assumptions.
Then you find problems with this "design", but that's your own faulty thinking which creates these problems.
Go back and think again, specially, watch for unheeded assumptions.
To highlight what a different approach could look like, see Jeffrey Elman's "An alternative view of the mental lexicon"
http://crl.ucsd.edu/~elman/Papers/elman_tics_opinion_2004.pdf
Not that this is likely to be the "one and true" answer either, but at least it is more thought out.
For a brain refreshener I would also recommend Alex Gross's "Is Evidence Based Linguistics the Solution? Is Voodoo Linguistics the Problem?"
http://languag2.home.sprynet.com/f/evidence.htm

Chris said...

Anon, I'm not sure I made either of those 2 assumptions. First, I used as an example two sentences that are quite easy for the vast majority of English speakers to understand (a fact empirically confirmed in the paper I cited). I'm not demanding a perfect listner, only one that can do the things that we do easily. Second, I spent the bulk of this post describing a situation in which neither the human listner nor the computer has a definition of the word in a lexicon. Instead, the human and the computer would have to retrieve many different concepts (I assume its uncontroversial that humans have concepts, and Fodor not withstanding, that they have content). But thanks for the references. I'll check them out.

Jim Davies said...

Nice Blog. I write a lot about Cognitive Science too, if you want to check it out.

http://jimdavies.blogspot.com/

John Black said...

This sounds similar to a conclusion I came to and wrote about in my blogpost, It Takes an Agent to be Semantic. And I also agree with you about the difficulty of this but I feel that progress in this area is on an exponential curve. Jeff Hawkins, with his company Numenta, may come up with something powerfull enough to come closer than ever before. I include some links to his work and express this idea further in The Semantic Web Awaits Real Semantic Machinery

Daniel said...

I generally don't talk to environmental scientists to find out what it's like to be a astronaut. Why would I talk to a computer to find out what it's like to be a human child with a busted leg? Any computer worth talking to would have insights that a human wouldn't, because their 'body' is different. Hopefully, such a computer would be curious about how we humans crutch balls, as well, and not wholly concerned with our complete destruction.

Fido the Yak said...

The discussion of affordances is fascinating. I question the statement made in Zhang's paper, "Affordances only make sense from a system point of view." To me it implies a reification, or making "system" do more than it needs to do. That is, if we allow that systems are real, empircally detectable phenomena, then we should be careful to distinguish a reference to that kind of system from the idea of a system as an explanatory model or useful all-purpose descriptor for a patterned assemblage of interrelations. I wouldn't want to actually describe something like an array of perceptual affordables without invoking the idea of a system, but neither would I want to make a commitment to its status before I had examined the matter.

If Gibson had in mind a particular kind of system, say an ecology of living organisms, but we take his use of "system" to be more generalizable, what will we have to account for if we apply his concept to phenomena lacking certain properties of the elements of an ecology?

What role does embodiment play in Gibson's system? Motility? Agency? Chris, perhaps you are correct that a body wouldn't be needed to understand affordances, but I think you will need something besides a large body of interconnected knowledge to account for the dynamic interplay between an organism and its environment. Isn't that the dynamic that makes Gibson's work interesting?

wholesale air jordan said...

Air Jordan shoes Air Jordan shoesjordan shoes
Air Jordan shoesjordans shoes
Cheap Jordans
wholesale jordan
Air Jordan shoes
wholesale air jordan
Nike Jordan Shoes
Nike Shoes Wholesale

wholesale air jordans Air Jordans
Wholesale Nike shoes Air Jordans
Air JordansWholesale Nike Air Jordans
Air JordansNike shoes Air Jordans
nike jordan Air Jordans
air jordan Air Jordans
Air Jordans Air Jordans

kiloi said...

tn chaussuresEnter the necessary language translation, up to 200 bytes winter, moves frequently in China, nike chaussures showing that the deep strategy of the Chinese market. Harvard Business School, nike tnaccording to the relevant survey data show that in recent years the Chinese market three brands, Adidas, mens clothingpolo shirts Li Ning market share at 21 percent, respectively, 20%, 17%. The brand is first-line to three lines of urban competition for mutual penetration. Side of theworld,announced layoffs, while China's large-scale facilities fists. The sporting goods giant Nike's every move in the winter will be fully exposed its strategy. Years later, the Nike, Inc. announced the world's Fan

shen bing said...

cheap hair straightenerscheap flat ironnew polo shirtssexy lingerie storepolo shirtsnorth face jacketschi straightenerpink chichaussures puma chaussure puma

shen bing said...

hair straightenersugg bootscheap handbagscheap bagscheap pursetntattoo wholesalejackets worldjackets cartmen's clothingwomen's clothing

shen bing said...

handbags Louis Vuitton Vuitton handbags Balenciaga Balenciaga Bally handbagsBottega Veneta handbagsCartier handbagsChanel handbagsChloe handbagsChristian Dior handbagsCoach handbagsDolce Gabanna handbags

shen bing said...

Fendi handbags Givenchy handbags Gucci handbags Hermes handbags Jimmy Choo handbags Juicy Couture handbags lsabella Fiore handbags Miu Miu handbags Mulberry handbags Prada handbags Tods handbags Versace handbags Yves Saint Laurent handbags

shen bing said...

Men's Lacoste Polo Shirts Men's RL Striped Polo Shirts Women's Lacoste Polo Shirts Men's polo shirts Men's polo shirts Men's polo shirts 4 polo shirts Women's polo shirts 21 polo shirts Men's polo shirts Women's LACOSTE 5 PCS of Ralph Women's lacoste polo shirts

crazyloko said...

China Wholesalers has been described as the world’s factory. buy products wholesaleThis phenomenom is typified by the rise ofbusiness. Incredible range of products available with China Wholesale “Low Price and High Quality” not only reaches directly to their target clients worldwide but also ensures that wholesale from china from China means margins you cannot find elsewhere and China Wholesale will skyroket your profits.china wholesale productsbuy china wholesalewholesale chinawholesale productsbuy products

crazyloko said...

We offer designer , custom wedding dress, cheap cell phonescheap wedding dressesbridal gowns, wedding gowns, Flower Girl Dresses andwholesale cell phonesso on. Buy tailor-made anddesigner wedding dresses designer to be a special brides now!

lady said...

I like the side of the article, and very like your blog, to write well and hope to continue their efforts, we can see more of your articles. ed hardy clothes. After reading this article has strong feelings, the future will be Changlaikankan's.ed hardy swimwear. polo hoodies
ed hardy jeans
ed hardy
ed hardy clothing
ed hardy t-shirts
ed hardy clothes
ed-hardy.co.uk
ed hardy shirts
ed hardy mens
ed hardy clothes
ed hardy womens
ed hardy sunglasses
ed hardy swimwear
ed hardy Jeans
ed hardy hoodies
ed hardy bags
ed hardy trousers
ed hardy shoes
ed hardy sunglasses
ed hardy suits
ed
hardy
ed hardy dresses
ed hardy boots
ed hardy mens sweater
ed hardy womens cotton
ed hardy womens boots

mamamia said...

Rare GHD
Babyliss
polo boots
polo shoes
cheap straighteners
ghd hair straighteners
hair straighteners
Purple GHD IV Styler
Pure White GHD
Pure Black GHD
Pink GHD IV Styler
Kiss GHD Styler
Gray GHD IV Styler
Gold GHD IV Styler
GHD Rare Styler
GHD IV Salon Styler
Black GHD IV Styler
Benefit GHD IV Styler

mamamia said...

herve leger
herve leger dresses
chanel
chanel iman
chanel outlet
chanel handbag
Chanel Wallet
Chanel Watch
chanel purse
Chanel Sunglasses
chanel bags
chanel earrings
chanel jewelry
chanel shoes

my blog said...

i want to show you the following products:
gucci boots
gucci shoes
gucci t-shirt
gucci bags
gucci handbags
gucci clothing
gucci watch
gucci sunglasses
gucci jewelry
gucci boots
gucci shoes
gucci t-shirt
gucci bags
gucci handbags
gucci clothing
gucci watch
gucci sunglasses
gucci jewelry
gucci boots
gucci shoes
gucci t-shirt
gucci bags
gucci handbags
gucci clothing
gucci watch
gucci sunglasses
gucci jewelry

xiansheng said...

rain boot
rainboots
rainboot
rain boots
rain coat
rain coat
raincoat
raincoats
rain coats
rain wear

abercrombie and fitch shirts
abercrombie outlet
abercrombie fitch outlet
abercrombie & fitch clothing
abercrombie and fitch clothes
abercrombie and fitch clothing
abercrombie fitch
abercrombie fitch clothing
abercrombie & fitch
abercrombie and fitch
abercrombie and fitch outlet
cheap abercrombie fitch
abercrombie shirtabercrombie fitch jacketabercrombie jacketabercrombie and fitch hoodiet

xiansheng said...

ankh royalty

ankhroyalty

ankh royalty clothing

ankh royalty sweats

ankh royalty tracksuits
babyliss
babyliss pro
babyliss hair
babyliss i trim
babyliss flat iron
babyliss you curl
babyliss hair straighteners
babyliss hair straightener
babyliss straightener
babyliss straighteners
babyliss portability
babyliss straightening irons
babyliss hair iron
babyliss straightening iron

Linn said...

adidas shoes
adidas shoe
adidas basketball shoes
adidas running shoes
adidas tennis shoes
adidas sneakers

Linn said...

jordan shoes
cheap jordan shoes
jordan 1
jordan 2
jordan 3
jordan 4
jordan 5
jordan 6
jordan 7
jordan 8
jordan 9
jordan 10
jordan 11
jordan 12
jordan 13
jordan 14
jordan 15
jordan 16
jordan 17
jordan 18
jordan 19
jordan 20
jordan 21
jordan 22
jordan 23
Michael Jackson memorial
air jordan 2009
air jordan 2010
jumpman 23

Hanthan said...

air max,Nike air max
air max 90
nike air max 90
air max 1
air max 95
nike air max 360
nike air max ltd
air max ltd
air max 360
air max classic,Air Max Huarache
air max light
air max bw
air max plus
air max 180
air max nike
air max TN
air max 87
timberland
timberland boots
timberland shoes
cheap timberland boots
timberland uk
timberlands
timberland 2010
timberland outlet

Hanthan said...

Armani Sunglasses
Burberry Sunglasses
Cartier Sunglasses
Chanel Sunglasses
Coach Sunglasses
D&G Sunglasses
Dior Sunglasses
ED Hardy Sunglasses
Fendi Sunglasses
LV Sunglasses
Oakley Sunglasses
Police Sunglasses
Ray Ban Sunglasses
Roberto Cavalli Sunglasses
Versace Sunglasses

Anonymous said...

I had never see a blog batter than this blog, I like this blog very very much.By the way, do you like my products: solar street lights, street lights, street lighting, street lamps, ball valves, butterfly valves, butterfly valve handles, check valves, sanitary fittings, butterfly valve handles, butterfly valve handles, street light, valve manufacturer, butterfly valve handles, valve manufacturers, butterfly valve handles, street lamp, solar street light, ball valve, butterfly valve handles, butterfly valve, check valve,valves manufacturers, butterfly valve handles

janewangleilei said...

jordan 18
jordan 19
jordan 20
jordan 21

janewangleilei said...

jordan 5
jordan 6
jordan 7

月月 said...

jordan 12
jordan 13
jordan 14
jordan 15
jordan 16
jordan 17 rings
jordan 18
jordan 19

janewangleilei said...

jordan 1
jordan 2
jordan 3
jordan 4
jordan 5
jordan 6
jordan 7

janewangleilei said...

air jordans shoes
micheal jordan
jumpman23
Air Jordan 2010
Jordan fusions
nike ajf shoes

barazhao said...

jordan 8
There are cheap shoes to choose
jordan 9
You can have a look at it.
jordan 10
Funny things like this.
jordan 11
jordan 12
jordan 13

daiyanren said...

There are cheap shoes to choose
jordan 6
jordan 7
Good quality with low price.
air jordan 2010
Air Jordan 2009
You can have a look at it.
jordan shoes
jordan ajf shoes
We offer different styles.
jordan 1
jordan 2
If you like,you can contact us.
jordan 3
jordan 4
Thanks.
jordan 5
jumpmen23

ally said...

It is very stylish and sleek. In the casual attire category tracksuits and tank tops rule for men. The most popular t-shirts this season would be the ones with funny sayings on them.cheap abercrombie fitch clothingdiscount abercrombie fitch T-shirtsdiscount abercrombie and fitch hoodiesabercrombie fitch outletwholesale abercrombie fitched hardy wholesale
cheap ed hardy wholesalediscount ed hardy wholesale
wholesale ed hardyed hardy outletdiscount abercrombie and fitch outletdiscount abercrombie outletdiscount abercrombie clothingdiscount abercrombie jacketdiscount abercrombie shirtdiscount abercrombie and fitch outletdiscount bercrombie and fitch clothesdiscount abercrombie and fitch hoodiediscount abercrombie and fitch shirtsdiscount abercrombie fitch jacketBesides, the urban trend, vintage clothing will also rule this season. This includes tight jeans and leather jackets and embroidered clothing.This season it seems like we are going to have a handful to choose from because the trend is a nice mix match of clothes from different seasons. So go ahead flaunt your style your own way.

ally said...

Apart from these military fashion tops and ripped and torn jeans are also hip and happening this season.2010 fashion trends for men would be dominated this season by denim. By denim we don't need to just stick to jeans but also sport denim jackets and casual pants as well. wholesale LV handbagsdiscount moncler jacketsmoncler coatsmonclermoncler vestmoncler outletmoncler t-shirtmoncler jacketsmonclernew moncler coatsmoncler vestmoncler outletmoncler polo t-shirtCoach handbags outletCheap Coach handbag 2010Discount Coach hand bagAuthentic Coach handbagNewest Coach handbags outletLouis Vuitton handbagsLV handbags 2010Discount LV handbagsCheap Louis Vuitton Outletnewest Louis Vuitton handbagscheap rain weardiscount rainweardog rain jacketscolorful rain bootsrainboots outletCheap Ture Religion Jeans outletDiesel JeansLevis JeansWholesale Ed Hardy JeansDiscount Dior Jeans outlet Jerseys and sneakers are never out of fashion. It is very urban and very hip hop.ust as leather is in trend for women it is also true for men. Leather jackets are a must in the wardrobe this season.

Michael J said...

I love your blog very much,and i also want to introduce my products to all of you,them are nice and very fashion,if you like them,please contact us on our website or eamil us,thks very much for your attention.And this is my products below:
authentic gucci bags, gucci boots outlet
cheap gucci shoes, discount Gucci bags
newest gucci handbags, gucci handbags 2010
Juicy couture, authentic Juicy bags
Juicy handbags outlet, tiffany 2010
Tiffany, tiffany outlet
discount tiffany charms, cheap tiffany Bangles
Armani watches outlet, watch wholesale
discount DG watches, cheap Chanel watches
newest GUCCI watches, wholesale edhardy t shirt
Moncler, Mtb shoes
Moncler jackets, cheap Moncler coats
Moncler Vest, Moncler outlet
moncler polo t shirt, MBT boots
MBT shoes in fashion, cheap mbt shoes sale
discount mbt outlet 2010, MBT Walking Shoes

Michael J said...

I love your blog very much,and i also want to introduce my products to all of you,them are nice and very fashion,if you like them,please contact us on our website or eamil us,thks very much for your attention.And this is my products below:
BABYLISS
Benefit GHD
GHD IV Salon Styler
GHD MINI STYLER
GHD Precious Gift Set
Gold GHD
Kiss GHD
Pink GHD
Pure Black GHD
Pure White GHD
Purple GHD
Rare GHD
cheap ugg boots
discount ugg boots
ugg boots
classic ugg boots
ugg classic tall boots