News for hackers. Stuff that matters.

A comment on The Illustrated Word2vec. Parent comment

Re:The Illustrated Word2vec by sixo on Wednesday March 27, 2019 @10:31AM (#19501125)
you could still interchange the dimensions arbitrarily. You can't say "dimension 1 = happiness", a re-training would not replicate that, and would not necessarily produce a dimension for "happiness" at all.
[ Parent | on HN ]
Re:The Illustrated Word2vec by b_tterc_p on Wednesday March 27, 2019 @11:43AM (#19502036)
I’m not saying that. I’m saying you could identify a linear combination of x,y,z that approximates happiness, and by doing this for many concepts, transform the matrix into an ordered state where each dimension on its own is a labeled concept.

People are quick to claim that embedding dimensions have no meaning, but if that is your goal, and your embedding space is good, you’re not terribly far from getting there.

[ Parent | on HN ]