Show HN: I made a word guessing game based on word semantic similarity

[ArneVogel]

This is inspired by [1] which was posted to HN two days ago [2]. In the blog the Jack describes this game: * Is it closer to Mussolini or bread? Mussolini. * Is it closer to Mussolini or David Beckham? Uhh, I guess Mussolini. (Ok, they’re definitely thinking of a person.) * Is it closer to Mussolini or Bill Clinton? Bill Clinton. * Is it closer to Bill Clinton or Pelé? Bill Clinton, I think. * Is it closer to Bill Clinton or Grace Hopper? Grace Hopper. * Is it closer to Grace Hopper or Richard Hamming? Richard Hamming. * Is it closer to Richard Hamming or Claude Shannon? You got it, I was thinking of Claude Shannon.

I wondered if it was possible to play this game against the computer [3]. I have solved this using the word vectors from GloVe: Global Vectors for Word Representation [4] and projecting them to 2d.

I am not 100% happy with how the game plays right now. It is hard to get closer to the target right now if you started "far away" from the target. That is why I have added the hints. If you have ideas for the game format let me know :)

[1] https://blog.jxmo.io/p/there-is-only-one-model [2] https://news.ycombinator.com/item?id=44595811 [3] https://xkcd.com/1425/ [4] https://nlp.stanford.edu/projects/glove/