sub-200 lol
Semantle #14 in 174 guesses. semantle.novalis.org
Conversation
Replying to
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
1
2
11
game state at the end
1
3
I think I'm overfitting on words with like 25 similarity and getting stuck in a local maximum instead of exploring more