|
|
|
|
|
by visarga
3035 days ago
|
|
An interesting property of word vectors (which are usually 300-600 dimensional vectors) is that most are quasi-orthogonal. That means when you sum them up, they compose well representing all the meanings of the component parts, and strangely, multi-sense words such as "bank" contain all the senses overlapped, yet distinct. Another interesting property is that high dimensional space has many shortcuts, or that at any point there are many paths. It's like a kaleidoscope with infinite reflections or like a mirror house. Or it's like any point has many close neighbours which can, paradoxically, be far apart between them. |
|
I think it would be more interesting if this wasn't the case. The set of all possible English words is <200,000, with probably 10% of those being in common use. Given the small set, large number of dimensions, and the nature of language, it seems likely that non-random word vectors would tend towards orthogonality.
I'm assuming you mean that, "I will run with Bob" and "I will jog with Stacy" are not orthogonal, because they convey a very similar message, but are orthogonal to, "Man, that was a good beer."