Slashdot Mirror
Words with Multiple Meanings Pose a Special Challenge To Algorithms (theatlantic.com)
Sample this: Me: So that's the marshmallow but you're going to eat it with this graham cracker and chocolate.
[My son looks at me like I am the dumbest person alive.]
Sebastian: No, I'm going to eat it with my MOUTH.
[End of play.] That's from "S'MORES. A Real-Life One-Act Play", a conversation between Hamilton impresario Lin-Manuel Miranda which his young son Sebastian. In that brief interaction, young Sebastian Miranda inadvertently hit upon a kind of ambiguity that reveals a great deal about how people learn and process language -- and how we might teach computers to do the same.
The misinterpretation on which the s'mores story hinges is hiding in the humble preposition with. Imagine the many ways one could finish this sentence: I'm going to eat this marshmallow with ... If you're in the mood for s'mores, then "graham cracker and chocolate" is an appropriate object of the preposition with. But if you want to split the marshmallow with a friend, you could say you're going to eat it "with my buddy Charlie." The Atlantic elaborates: Somehow speakers of English master these many possible uses of the word with without anyone specifically spelling it out for them. At least that's the case for native speakers -- in a class for English as a foreign language, the teacher likely would tease apart these nuances. But what if you wanted to provide the same linguistic education to a machine?
As it happens, just days after Miranda sent his tweet, computational linguists presented a conference paper exploring exactly why such ambiguous language is challenging for a computer-based system to figure out. The researchers did so using an online game that serves as a handy introduction to some intriguing work currently being done in the field of natural language processing (NLP). The game, called Madly Ambiguous , was developed by the linguist Michael White and his colleagues at Ohio State University. In it, you are given a challenge: to stump a bot named Mr. Computer Head by filling the blank in the sentence Jane ate spaghetti with ____________. Then the computer tries to determine which kind of with you intended. Playful images drive the point home. [Editor's note: check the article for corresponding images.]
In the sentence Jane ate spaghetti with a fork, Mr. Computer Head should be able to figure out that the fork is a utensil, and not something that is eaten in addition to the spaghetti. Likewise, if the sentence is Jane ate spaghetti with meatballs, it should be obvious that meatballs are part of the dish, not an instrument for eating spaghetti.
[My son looks at me like I am the dumbest person alive.]
Sebastian: No, I'm going to eat it with my MOUTH.
[End of play.] That's from "S'MORES. A Real-Life One-Act Play", a conversation between Hamilton impresario Lin-Manuel Miranda which his young son Sebastian. In that brief interaction, young Sebastian Miranda inadvertently hit upon a kind of ambiguity that reveals a great deal about how people learn and process language -- and how we might teach computers to do the same.
The misinterpretation on which the s'mores story hinges is hiding in the humble preposition with. Imagine the many ways one could finish this sentence: I'm going to eat this marshmallow with ... If you're in the mood for s'mores, then "graham cracker and chocolate" is an appropriate object of the preposition with. But if you want to split the marshmallow with a friend, you could say you're going to eat it "with my buddy Charlie." The Atlantic elaborates: Somehow speakers of English master these many possible uses of the word with without anyone specifically spelling it out for them. At least that's the case for native speakers -- in a class for English as a foreign language, the teacher likely would tease apart these nuances. But what if you wanted to provide the same linguistic education to a machine?
As it happens, just days after Miranda sent his tweet, computational linguists presented a conference paper exploring exactly why such ambiguous language is challenging for a computer-based system to figure out. The researchers did so using an online game that serves as a handy introduction to some intriguing work currently being done in the field of natural language processing (NLP). The game, called Madly Ambiguous , was developed by the linguist Michael White and his colleagues at Ohio State University. In it, you are given a challenge: to stump a bot named Mr. Computer Head by filling the blank in the sentence Jane ate spaghetti with ____________. Then the computer tries to determine which kind of with you intended. Playful images drive the point home. [Editor's note: check the article for corresponding images.]
In the sentence Jane ate spaghetti with a fork, Mr. Computer Head should be able to figure out that the fork is a utensil, and not something that is eaten in addition to the spaghetti. Likewise, if the sentence is Jane ate spaghetti with meatballs, it should be obvious that meatballs are part of the dish, not an instrument for eating spaghetti.
Want a context-free language, easily parseable, with plenty of computer-driven tooling, without this irritating English ambiguity? Lojban is learnable today: https://mw.lojban.org/papri/la...
In all seriousness, it is mind-blowing to me that our tribe of computer scientists continue to expend so much effort deriving meaning from English utterances. If we only wanted to encode meaning in a computer-manageable way, we could have been doing it decades ago.
~ C.
These two people can be on the same side in WWII:
"I'm going to fight with the Allies."
"I'm going to fight with Hitler."
THis really isn't that complicated. It's not that words have two meaning but there are different cases. In many languages there is a dative suffix for words taking a supporting roll. I threw the ball out the window. case endings can cleanly separate subject (I), direct object (ball) and participating clause object (window). IN english we lack a dative suffix on most words. So we have helper words and word orders to tell us which are the dative.
In the case of all the examples give, "with" here is just saying the object named participated. "fork, meatball, Buddy". It doesn't say how it participated. That is completely not the content of the sentence.
the point I'm making is that the sentence scans identically. It's not ambiguous. It's exact. It's entirely possible that I ground up my buddy to make meatballs out of him and that I actually like eating small forks. That information is not intended to be present. It would come from external context. The senstence is not ambiguous.
Some drink at the fountain of knowledge. Others just gargle.
Me: Your new magazine you got from your grandmother for your birthday came in the mail. Do you want to read it tonight for bedtime?
4yo: [Confused] Magazines aren't for reading.
Me: What are they for?
4yo: [Stated with an tone of obviousness] Magazines are for cutting.
[End scene]
Time flies like an arrow
Fruit flies like a banana.
Vey smart people have found that in the 1970, 1980, 1990. 2000... 2018. With decades of funding and experts.
https://en.wikipedia.org/wiki/...
Maybe some Seeding Intelligence https://www.wired.com/1997/07/...
"...program only basic behaviors into the device, give it a way to experience sensory perception, and allow it to learn from experience.. "
Domestic spying is now "Benign Information Gathering"
Children are very highly specialized in reducing an argument to absurdity. This is a very important tool in logic and, in my opinion, it is no better exemplified elsewhere other than in Lewis Carroll's books, which I think is why Miranda's kid interpreted his father's statement as absurd. As a mathematician, Carroll was quite aware of how easily logical errors come about. I like citing when Humpty Dumpty explains what an un-birthday is to Alice: “I mean, what is an un-birthday present?" A present given when it isn't your birthday, of course." Alice considered a little. "I like birthday presents best," she said at last. You don't know what you're talking about!" cried Humpty Dumpty. "How many days are there in a year?" Three hundred and sixty-five," said Alice. And how many birthdays have you?" One.” I suppose Miranda could have been more explicit and said "along with", rather than just using "with" alone. As another example of this, we say "a glass of water", despite the glass not being made of water. Yet we don't say "a glass with water". And we certainly don't drink the glass, but rather its contents. I find all this fascinating. Brits have trouble understanding some American phrases as well for pretty much the same reason. Same thing goes for European Spanish and Latin American Spanish. Maybe feeding an AI with several samples of such phrases, as said and interpreted by multiple cultures would better train it to deal with such "inconsistencies"?
jane ate spaghetti with dick.
Now .. what does that mean?
Take a look at it and give yourself a treat.
the fuck did I just read?
Only the State obtains its revenue by coercion. - Murray Rothbard
But context gets complicated, quickly. And when things get too complicated, managers and grad students retreat to their happy places. End of AI story.
Strange things are afoot at the Circle-K.
If that shit can't figure the fuck I mean, then shit's on them, so fuck 'em! Fuck those fucking fuckers because no fucks given for that shit. ;)
Anons need not reply. Questions end with a question mark.
Context comes from our knowledge about those objects. We know a great deal about utensils. We know about what's food and what isn't based upon both what we've eaten in the past, as well as what society mores allow. It's one of the reasons the first delving into AI consisted in codifying a lot of human knowledge into a idiot savant, but brittle outside it's sphere of knowledge.
I've always thought that if you know code and/or other artificial languages the next real challenge is trying to use it to decipher human natural languages. A person learns really quickly the huge amounts of strange quirks and mental leaps we humans have to make just to communicate somewhat rationally. When we actively choose to do so anyway.
There's even whole other worlds of artificially structured "semi-natural" languages used to define things further to prevent and/or promote misunderstanding. An incomplete list might read as: technical writing, political speech, legal documents, formal and informal language.
News at 11.
Oh Reaaallly??
Next, you're going to tell me they have trouble with sarcasm.
Let's eat, Grandma.
Let's eat Grandma
Hmm...I think this is where things went wrong with Skynet, someone left out the comma!
Ambiguity exists in all natural languages, and in many forms.
When humans find the contextual reference vague or ambiguous they usually query for more information. Can't machines do this as well?
Everything in the Universe sucks: It's the law!
... words with Multiple Meanings Pose a Special Challenge To Autistics. /yawn
I couldn't have said it better myself! https://twitter.com/iamdevlope...
Cyc has been working on this for quite a while and actually has products available.
Another example of the challenges:
She saw the bicycle in the window and wanted it.
What did she want? The window or the bike?
When Fascism comes to America, it will call itself Anti-Fascism, and tell you to give up your guns.
They try to teach math the same way, assuming people will just figure out the context to solve problems. Newflash, it isnt working very well.
I object to power without constructive purpose. --Spock
that was the point. This illustrates that for fighting, "with X" can mean who you're allied to or who you're opposing (admittedly, the opposition form is less common than "against" or no word at all "I'm fighting Hitler").
In Japanese, the "with" meaning "using this tool" would be the particle "de". "with" meaning "together" would be the particle "to", but without further elaboration, there's still ambiguity between "eat two ingredients together" and "two participants eat together" depending on how the sentence got constructed. Who knows an actual language people use that makes this completely unambiguous?
-- "This world is a comedy to those who think, a tragedy to those who feel."
An example for clarity:
Bob: What's wrong?
Steve: I'm fighting with my wife.
This is known as word sense disambiguation - there are a number of ways to do so. Training systems for disambiguation is more resource intensive, and in many use cases provides little gain, so most don't bother.
https://en.wikipedia.org/wiki/...
"The misinterpretation on which the s'mores story hinges is hiding in the humble preposition with."
In this case "with" acts as a noun -- the word "with" and not a preposition.
The main context is called "general", akin to "void main( argc, argv)" (in C/C++). Each context consists of a sequence of recognizers (patterns for recognizing user statements), organized from longest (number of pertinent words) to shortest. For example, in MorgaScript (I think (and hope) any programmer could figure out how this works by looking at it):
Context "general"
Synonyms yes: yep, yeah, sure
Synonyms no: nope, nah, no way
Group personName: "Jane", "Joe", "Jim"
Group foodType: "spagetti", "smores"
Remember "third person possessive term for female is her"
Remember "Jane's gender is female"
Recognizer "[person:personName] ate [food:foodType] with [toolType:tool]"
Option
Recall "[person]'s gender is [gender]"
Recall "third person possessive term for [gender] is [possterm]"
Say "Did [person] find using a [tool] convenient for eating [possterm] [food]?"
Expect "yes" As "[person] likes to eat using [tool]."
Expect "no" As "[person] does not like to eat using [tool]."
Recognizer "[person:personName] ate [food:foodType] with [foodType:other]"
Option
Recall "[person]'s gender is [gender]"
Recall "third person possessive term for [gender] is [possterm]"
Say "Did [person] find the combination of [food] and other more delicious than [food] alone?"
Expect "yes" As "[person] likes [food] with [other]."
Expect "no" As "[person] does not like [food] with [other]."
Context "whatever" ..
You can use the command "Enter" followed by a context name to activate a context and put it first in the cascading priority. Similarly, "Exit" followed by the context name deactivates the named context. Recognizers are checked in order of highest to lower priority context, and longest to shortest within contexts. Any recognizer matched within a context, moves that context to the top priority automatically.
You could use contexts to do what is said.. or you could just use the method I used above... classifying different types of foods and tools.
Thanks -- I have made many version of this kind of thing and my latest Moringa Agent Engine is probably a few days from it's 1.0 release.
Matthew C. Tedder
In natural language processing polysemous words in a dictionary are often discerned with hashes. In the example above "with", with respect to "with graham crackers", would have one hash, whereas "with" with respect to "with my friend", would have a different hash. Through a well-developed NLP algorithm, and a lot of training, discerning between the two different contexts is certainly doable.
We overlap contexts to resolve ambiguities. One could think of English's object orientation like this (with comments to the right of each line):
a dog sat in the yard. // instantiate class "dog" // assign "hair" attribute of the last instantiated instance of the "dog" class // instantiate class dog // refers to the last dog instantiated. // refers to the last dog with the aforementioned brown hair attribute.
The dog's hair is brown.
a dog is running down the road.
The dog is fast.
The dog with brown hair is slow.
In other words, we always refer to the last version of whatever it is (instance of class) that has whatever attributes we ascribe it is..
This was already known in the 60s, but that did not prevent the AI community to hype things even more extravagantly than today. How much longer before the next AI Winter?
That's from "S'MORES. A Real-Life One-Act Play", a conversation between Hamilton impresario Lin-Manuel Miranda which his young son Sebastian
Surely the word "with" should have been used instead of "which" in that sentence.
When Kiddo was 2 or 3 years old he was using his plastic dinos to make dino tracks in Silly Putty. Eventually he made so many tracks that the Silly Putty was nothing but a bunch of marks. I wanted to make some fresh tracks with a different dino so I said
"Here, let me make it smooth" and I rolled it between my two palms making it into a smooth ball and I showed it to him
"Can I have the smooth?" he asked.
I smiled because he took the word smooth to describe the shape of it, not the texture of it.
For instance if you say Jane ate spaghetti with veramissimo no one knows what you're talking about until you know whether that's an herb, an adjective, or a utensil.
Just another second banana
Now I wonder how these algorithms deal with this sentence:
A ship shipping ship, shipping shipping ships.
Time to offend someone
I'll eat spaghetti with hot grits in my pants.
Why should NLP remain sane?
Aah, change is good. -- Rafiki
Yeah, but it ain't easy. -- Simba
"Use context? Sorry Dave, I don't know how."
Table-ized A.I.
I will leave you with some chicken https://www.youtube.com/watch?....
Corporate Gadfly
Jonathan Archer: the most beaten up Enterprise captain in Star Trek history
https://www.youtube.com/watch?...
Buffalo buffalo buffalo buffalo buffalo buffalo buffalo.
Similar sentences exist in other languages.
German: Die Männer, die vor dem Schokoladenladen Laden laden, laden Ladenmädchen zum Tanzen ein, meaning "The men, who loaded chests in front of the chocolate shop, asked shop girls for a dance".
Or Wenn hinter Fliegen Fliegen fliegen, fliegen Fliegen Fliegen nach, meaning "When flies fly behind flies, flies fly after flies".
Danish, Swedish, and Norwegian: Bar barbarbarbarbar bar bar barbarbarbarbar, meaning "naked barbarian-bar-barbarian [barbarian usually hanging out in bars for barbarians] carried naked barbarian-bar-barbarian."
Or Når graver Graver graver grave, graver graver Graver grave for andre, meaning "When digger Graver [his name is Graver] digs graves, digger Graver digs graves for others."
Spanish: Cómo como? Como como como, meaning "How do I eat? I eat the way I do".
Dutch: Als achter vliegen vliegen vliegen vliegen vliegen vliegen achterna, meaning "If flies fly behind flies, then those flies are flying behind flies".
Or "Als graven graven graven graven graven graven graven graven", meaning "When counts dig graves for other counts, counts are digging graves for other counts".
for Oxymoron statements
Casteism