Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A Simple AI Capable of Basic Reading Comprehension

blog.ayoungprogrammer.com

Post reply on HN
Print view View original

11–20 of 64 posts

Re: A Simple AI Capable of Basic Reading Comprehension

#11

Post by RHSeeger »

mratzloff wrote: post #6

Some thoughts about creating a system like this: Any successful implementation of comprehension must progressively enhance the world model based on additional information. Furthermore it must understand some basic rules, such as, "Any subject, set of subjects, or actions can be represented multiple ways." So if you said, "Mary's brother is Sam," or "Mary has a brother named Sam," or "Mary's brother is named Sam," the…

> Further, if you mention that John also has a brother named Sam, and then you mention Sam in an ambiguous context, the program should be smart enough to ask, "Which Sam? Mary's brother or John's?"

Option 3: The only Sam, since Mary and John are brothers :)

Re: A Simple AI Capable of Basic Reading Comprehension

#12

Post by kaffeemitsahne »

dave_sullivan wrote: post #8

Not to be discouraging, but I think research along these lines http://arxiv.org/abs/1503.08895 stands an exponentially better chance of leading towards what OP is talking about. For anyone interested in "building AI", read that paper and all it's references.

Just because it could be done with the current hip thing (neural nets) doesn't mean all other approaches should be disregarded.

Re: A Simple AI Capable of Basic Reading Comprehension

#13

Post by phkahler »

phkahler wrote: post #10
mratzloff wrote: post #6

Some thoughts about creating a system like this: Any successful implementation of comprehension must progressively enhance the world model based on additional information. Furthermore it must understand some basic rules, such as, "Any subject, set of subjects, or actions can be represented multiple ways." So if you said, "Mary's brother is Sam," or "Mary has a brother named Sam," or "Mary's brother is named Sam," the…

>> Finally, there is also the concept of confidence. In the face of ambiguity that can't be resolved, a confidence rating should be assigned based on available information and future answers should be based on that confidence. That should probably be the first thing ;-) Every word has a probable meaning, and when all of them fit together into a coherent way including context, then the meaning is correct (probably). T…

In the blog comments someone raises proposes the sentence "Mary saw the jaguar". And points out that it wouldn't know if the jaguar was an animal or a car. Once again, confidence comes in but it would be based on context. Or perhaps it would become clear after more conversation.

Re: A Simple AI Capable of Basic Reading Comprehension

#14

Post by nyamhap »

borkabrak wrote: post #7

I love the ambition. But when you stated your next goals, I'm afraid I thought of this: http://xkcd.com/1425/ I may very well be wrong, and I'd love it if you showed me I am. Good luck. As I said, I really would be excited to see this go farther.

When was that xkcd posted? - couldn't not find a date.

Since machine vision is such a fast moving field, I think date is relevant for understanding the context of this xkcd. Is image recognition of a bird so inconceivable at the moment? Perhaps the joke now would be - "I'll need one researcher and one year"

Re: A Simple AI Capable of Basic Reading Comprehension

#16

Post by dave_sullivan »

kaffeemitsahne wrote: post #12
dave_sullivan wrote: post #8

Not to be discouraging, but I think research along these lines http://arxiv.org/abs/1503.08895 stands an exponentially better chance of leading towards what OP is talking about. For anyone interested in "building AI", read that paper and all it's references.

Just because it could be done with the current hip thing (neural nets) doesn't mean all other approaches should be disregarded.

They're the current hip thing because they work really well and keep working better. They take a fundamentally different (I think better) approach than he's taking.

My recommendation comes from a more informed place than "Dur, neural networks!" Of course, this is my opinion, and you are welcome to have a different one.

What is your recommendation on the topic of most promising research areas for teaching reading comprehension to computers? Skip deep learning and read what instead? Or the OP has it figured out?

Re: A Simple AI Capable of Basic Reading Comprehension

#18

Post by ganarajpr »

nyamhap wrote: post #14
borkabrak wrote: post #7

I love the ambition. But when you stated your next goals, I'm afraid I thought of this: http://xkcd.com/1425/ I may very well be wrong, and I'd love it if you showed me I am. Good luck. As I said, I really would be excited to see this go farther.

When was that xkcd posted? - couldn't not find a date. Since machine vision is such a fast moving field, I think date is relevant for understanding the context of this xkcd. Is image recognition of a bird so inconceivable at the moment? Perhaps the joke now would be - "I'll need one researcher and one year"

One researcher and a month ( perhaps even less ! ) is more like it..

Re: A Simple AI Capable of Basic Reading Comprehension

#19

Post by kaffeemitsahne »

dave_sullivan wrote: post #16
kaffeemitsahne wrote: post #12

Earlier quoted context omitted.

Just because it could be done with the current hip thing (neural nets) doesn't mean all other approaches should be disregarded.

They're the current hip thing because they work really well and keep working better. They take a fundamentally different (I think better) approach than he's taking. My recommendation comes from a more informed place than "Dur, neural networks!" Of course, this is my opinion, and you are welcome to have a different one. What is your recommendation on the topic of most promising research areas for teaching reading comp…

I think the strength lies in combining NNs with less fuzzy approaches (like the OP, or more explicit pattern matching). Coulda made that a bit clearer, I have to admit. Cuz who would want to spend an hour training their net on a big GPU for every new command they add? :P

To take a concrete example: we trust neural networks to do the handwriting recognition at the postal office, but once the address is digitized we use a simple database.

Re: A Simple AI Capable of Basic Reading Comprehension

#20

Post by mratzloff »

phkahler wrote: post #10
mratzloff wrote: post #6

Some thoughts about creating a system like this: Any successful implementation of comprehension must progressively enhance the world model based on additional information. Furthermore it must understand some basic rules, such as, "Any subject, set of subjects, or actions can be represented multiple ways." So if you said, "Mary's brother is Sam," or "Mary has a brother named Sam," or "Mary's brother is named Sam," the…

>> Finally, there is also the concept of confidence. In the face of ambiguity that can't be resolved, a confidence rating should be assigned based on available information and future answers should be based on that confidence. That should probably be the first thing ;-) Every word has a probable meaning, and when all of them fit together into a coherent way including context, then the meaning is correct (probably). T…

I'd also go as far as saying part of the internal model of the world should also have a confidence. Any failure to understand a sentence may actually be a problem with its world view.

Yes, but that happens automatically by virtue of learning through natural language teaching. Put the VI through school.

Post reply on HN