Meaning of a symbol is a set of vectors -> What is the operation of the meaning?

• If meaning of symbol is set of vector, what can be the semantic operation?

  • k-method etc. is an operation that turns vector set into a set of vectors.
  • The operation of simply averaging a set of vectors is equivalent to the k-means method with k=1
  • A kind of = abstraction that ignores differences between individual vectors and combines them into one.
  • projection
  • There was talk of being crushed in the middle of something being an abstraction, of the vector of meaning.
  • The same can be done for a set of vectors

• Find the distance

  • Given multiple sets of vectors, find the distance between them
  • This means applying hierarchical clustering to meanings

---

This page is auto-translated from /nishio/シンボルの意味がベクトルの集合→意味の演算は？ 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.