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

Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding [pdf]

arxiv.org

Post reply on HN
Print view View original

1–10 of 25 posts

Re: Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding [pdf]

#3

Post by dschiptsov »

In accuracy of decoding (pattern matching)? What it had to do with IQ?

The decades old system for handwriting digits recignition for US Post beated humans (now it is a few lines of Octave in Andrew Ng's course). Still it cannot write a reply to a letter.)

Re: Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding [pdf]

#4

Post by Houshalter »

jyzzmoe wrote: post #2

And yet ... http://arxiv.org/pdf/1412.1897v1.pdf%EF%BB%BF

Not really relevant to this. That deals with images, where you can perturb a huge number of pixels slightly to exploit weird edge cases. Even linear classifiers break on it, e.g. https://karpathy.github.io/2015/03/30/breaking-convnets/

Re: Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding [pdf]

#5

Post by joe_the_user »

dschiptsov wrote: post #3

In accuracy of decoding (pattern matching)? What it had to do with IQ? The decades old system for handwriting digits recignition for US Post beated humans (now it is a few lines of Octave in Andrew Ng's course). Still it cannot write a reply to a letter.)

I'm reading the article and it's talking about solving analogies, antonyms and similar problems ... as found on a standard IQ test.

I understand this isn't intelligence and the title doesn't imply it but I'm not sure what your reference to decoding is about.

Re: Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding [pdf]

#7

Post by clickok »

Interesting and cool. It's almost like a magic trick, particularly in the sense that an almost unbelievable result has been achieved through putting in a serious amount of effort. It's not just a gimmick, though-- projects like this demonstrate the steady creep of progress on seemingly unsolvable problems[1]. But of course, there's thousands of such problems out there, with millions of potential customers ready to make whoever solves one a billionaire, so even if "true" AI fails to appear, odds are good we'll make a fair approximation for specific applications.

One thing that popped out at me, however, was the distribution of the human scores: monotonically increasing with age, which was somewhat odd. Shouldn't it be more or less normally distributed?

1. I wouldn't have thought to make a serious attempt towards beating a verbal comprehension test with deep learning; the possibility of succeeding would've seemed tiny in compared to the work. Similar to the notion that trying to prove the Riemann Hypothesis is hard to think of as a real pursuit, at best it's like a quixotic hobby.

Re: Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding [pdf]

#9

Post by dschiptsov »

joe_the_user wrote: post #5
dschiptsov wrote: post #3

In accuracy of decoding (pattern matching)? What it had to do with IQ? The decades old system for handwriting digits recignition for US Post beated humans (now it is a few lines of Octave in Andrew Ng's course). Still it cannot write a reply to a letter.)

I'm reading the article and it's talking about solving analogies, antonyms and similar problems ... as found on a standard IQ test. I understand this isn't intelligence and the title doesn't imply it but I'm not sure what your reference to decoding is about.

But it still seems like pattern recognition based on a training set only, which is, in my opinion, a task on a lever prior to intelligence, like what visual cortex does. It cannot make new reference between words to produce (infer) new antonyms and analogies (not presented in a training g set), which is intelligence.
Post reply on HN