SUB-100 FINALLY
Semantle #15 in 90 guesses. semantle.novalis.org
Conversation
basically same strategy as semantle #14, thought in terms of co-occurrence in similar documents. again ran into a mild issue with polysemous words but now that i know to look for it it's manageable
Quote Tweet
today i tried thinking a lot more about what words were likely to occur in similar positions in similar documents in word2vec’s training set and that worked a lot better than trying to use raw semantic distance only
Show this thread
1
4
the main mental move i'm doing is something like maintaining a "light grip" on what i think the word is "about." like too tight a grip and i don't move far away enough, too loose a grip and there are too many options where to go next
1
6
also slowly developing more of an intuition for what the similarity numbers mean. below 15 or so is incredibly noisy, 25ish is roughly when you're really getting somewhere it seems like?
4
4
this gamification of developing intuition for neural nets is... brilliant. I kind of want to build a generic version of this for any model, it actually seems like a great way to QA them
1
3
Replying to
hahaha I could do phrasle; like semantle but with whole phrases. give a live update of the proximity as you type, maybe...
1
1
a little feedback would be great. Could do it like the game French Toast.
If your new guess is the closest, that's all you know.
If it's not the closest, look at a dimension it is closer in. Pick a very that dimension word as a clue
1