Embedding
Version 1.0.0 · Updated 2026-07-30
CORE DEFINITION
Mapping words or concepts into a high-dimensional vector space. In this space, semantically similar words are closer in distance. For example, "king - man + woman ≈ queen".
SCAFFOLDING EFFECT
Reduce cognitive load
Geometrization of meaning. Concepts are not isolated; they have definite positions and distances in semantic space. Through this geometric thinking, we can perform "concept arithmetic"—adding two seemingly unrelated idea vectors to find their intersection in semantic space (new ideas).
Anchor fast decisions
By training neural networks on large-scale corpora, discrete symbols (words, sentences, documents) are projected into a continuous vector space; the model aims at "context prediction" (e.g., Skip-gram, CBOW), so that tokens that co-occur frequently or are semantically similar obtain similar vectors. The geometric relationships of vectors encode semantics and syntax, enabling analogical operations such as vector addition and subtraction.
MINIMUM ACTION
In progress 0/4Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- en.wikipedia.orghttps://en.wikipedia.org/wiki/Embeddingverified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS