word2vec – Tool for computing continuous distributed representations of words

Re:word2vec – Tool for computing continuous distributed repr... by quentinp on Thursday August 15, 2013 @03:22AM (#6216561)

You can think of this as a square matrix W. The size of the matrix is the size of the vocabulary. If we look at the 100k most frequent words in our corpus, W will be a 100k x 100k matrix.

The value of W(i,j) is the distance between words i and j, and a row of the matrix is the vector representation of that word. Research around word vectors is all about computing W(i,j) in an efficient way that is also useful in natural language processing applications.

Word vectors are often used to compute similarity between words: since words are represented as vectors, we can compute the cosine angle between a given pair of words to find out how similar the two words are.

[ Parent | on HN ]

Re:word2vec – Tool for computing continuous distributed repr... by rcfox on Thursday August 15, 2013 @04:01AM (#6216641)

Does that mean there actually is an answer for "What do you get when you cross a mosquito with a mountaineer?"

[ Parent | on HN ]

Re:word2vec – Tool for computing continuous distributed repr... by SergeyHack on Saturday August 17, 2013 @06:40AM (#6228729)

TL;DR: The answer to your query is a person named Chaudhry Sitwell Borisovich who is definitely an entomologist-hymnist and probably is also a mineralogist-ornithologist.

A google search suggests that he was born in 1961.

I ran a few queries using the code and its default dataset, trying to use neutral words for substraction: "mosquito -small +mountaineer", "mosquito -big +mountaineer", "mosquito -loud +mountaineer", "mosquito -normal +mountaineer", "mosquito -usual +mountaineer", "mosquito -air +mountaineer", "mosquito -nothing +mountaineer".

The most frequent words for these queries are:

6 times: "borisovich" "chaudhry" "entomologist" "hymnist" "sitwell"

5 times: "mineralogist" "ornithologist"

[ Parent | on HN ]

Re:word2vec – Tool for computing continuous distributed repr... by rcfox on Sunday August 18, 2013 @01:36AM (#6231789)

Well done, sir.

[ Parent | on HN ]

Re:word2vec – Tool for computing continuous distributed repr... by sixbrx on Thursday August 15, 2013 @07:00AM (#6217089)

Well you can dot them if not cross them (cross needs 3 dimensions iirc)!

[ Parent | on HN ]

Re:word2vec – Tool for computing continuous distributed repr... by defen on Thursday August 15, 2013 @11:27AM (#6218380)

You inadvertently stumbled onto the punchline of the joke - "You can't cross them because a mountaineer is a scalar." (scaler) - works better when spoken.

[ Parent | on HN ]

Re:word2vec – Tool for computing continuous distributed repr... by sp332 on Thursday August 15, 2013 @03:30PM (#6220027)

Don't forget the part about the mosquito being a vector :)

[ Parent | on HN ]