Solving Verbal Comprehension Questions in IQ Test by Knowledge-Powered Word Embedding · HackerPapers discussions

Solving Verbal Comprehension Questions in IQ Test by Knowledge-Powered Word Embedding — mentioned by Houshalter

Thu, 31 Dec 2015 15:57:20 GMT

Here is the most up to date version of the paper: http://arxiv.org/pdf/1505.07909.pdf The questions on the IQ test are very specific. Word analogies, identifying antonyms, synonyms, and which word isn't like the others. The method they use is similar to word2vec. That is, it does statistics on millions of words and how they occur in sentences to try to create a vector representation of it. These vector representations include a lot of semantic information about the words and what they mean, which makes it possible for the computer to do these tests automatically. They then compared it's…

Paper and discussion history. A mention is not an endorsement.

Solving Verbal Comprehension Questions in IQ Test by Knowledge-Powered Word Embedding — mentioned by mbq

Thu, 31 Dec 2015 14:57:06 GMT

This is only for certain, verbal questions like antonym of, synonym of, X is to Y as Z to what; for each of them a separate, specific model was built (not that the AI read the question and printed relevant answer). To sum up, the paper should be titled "Dictionary is better than MechTurk users on look-in-dictionary tasks." Link to the original paper: http://arxiv.org/pdf/1505.07909v1.pdf

Paper and discussion history. A mention is not an endorsement.

Solving Verbal Comprehension Questions in IQ Test by Knowledge-Powered Word Embedding — HN submission

Mon, 15 Jun 2015 00:52:00 GMT

Solving Verbal Comprehension Questions in IQ Test by Word Embedding

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Solving Verbal Comprehension Questions in IQ Test by Knowledge-Powered Word Embedding — HN submission

Sat, 13 Jun 2015 01:42:50 GMT

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

80 points; 21 discussion replies on HN. Paper and source history. A submission is not an endorsement.