←back to thread

Show HN: Semantic Calculator (king-man+woman=?)

(calc.datova.ai)
176 points nxa | 1 comments | 14 May 25 19:54 UTC | HN request time: 0.208s | source

I've been playing with embeddings and wanted to try out what results the embedding layer will produce based on just word-by-word input and addition / subtraction, beyond what many videos / papers mention (like the obvious king-man+woman=queen). So I built something that doesn't just give the first answer, but ranks the matches based on distance / cosine symmetry. I polished it a bit so that others can try it out, too.

For now, I only have nouns (and some proper nouns) in the dataset, and pick the most common interpretation among the homographs. Also, it's case sensitive.

Show context
montebicyclelo ◴[14 May 25 21:41 UTC] No.43989512[source]▶
> king-man+woman=queen

Is the famous example everyone uses when talking about word vectors, but is it actually just very cherry picked?

I.e. are there a great number of other "meaningful" examples like this, or actually the majority of the time you end up with some kind of vaguely tangentially related word when adding and subtracting word vectors.

(Which seems to be what this tool is helping to illustrate, having briefly played with it, and looked at the other comments here.)

(Btw, not saying wordvecs / embeddings aren't extremely useful, just talking about this simplistic arithmetic)

replies(7): >>43989576 #>>43989687 #>>43989933 #>>43989963 #>>43990416 #>>43990646 #>>43995277 #
1. groby_b ◴[14 May 25 22:45 UTC] No.43989963[source]▶
I think it's worth keeping in mind that word2vec was specifically trained on semantic similarity. Most embedding APIs don't really give a lick about the semantic space

And, worse, most latent spaces are decidedly non-linear. And so arithmetic loses a lot of its meaning. (IIRC word2vec mostly avoided nonlinearity except for the loss function). Yes, the distance metric sort-of survives, but addition/multiplication are meaningless.

(This is also the reason choosing your embedding model is a hard-to-reverse technical decision - you can't just transform existing embeddings into a different latent space. A change means "reembed all")