• Imagine that the distributed representation of a character is placed in the same vector space as the Distributed representation of words.
  • The word “unknown” and the letters “un,” “know,” and “word” are placed in the same space.
  • The closest thing to an “unknown word” would be “word.”
  • If sets X and Y are arranged in the same vector space, then for element x of set X, we can say “What would you dare to express this in Y?
  • What is the closest word to “un.”

image


This page is auto-translated from /nishio/文字の分散表現 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.