embedding

embedding (plural embeddings)

1. The act or process by which one thing is embedded in another.
2. (mathematics) A map which, in any of several technical senses, represents the containment of one structure inside another.
   1. (topology) A continuous map which is also a homeomorphism between its domain and its image (considered with the subspace topology induced by its codomain).
   2. (differential topology) An immersion which is also a topological embedding; equivalently, a diffeomorphism whose image is a submanifold of its codomain.
   3. (field theory, Galois theory) A ring homomorphism between fields (the name deriving from the fact that all such maps are injective).
   4. (mathematical analysis) A map between metric spaces which preserves distances up to some scaling factor (called the distortion).
   5. (category theory) A injective morphism in a concrete category which is also initial.
3. (machine learning, artificial intelligence) A representation of a unit of text (such as a word or token) as a vector, which encodes the context in which it is used.

   word embeddings

   • 2017 April 13, Hannah Devlin, quoting Arvind Narayanan, “AI programs exhibit racial and gender biases, research reveals”, in The Guardian‎^[1], →ISSN:

     “A major reason we chose to study word embeddings is that they have been spectacularly successful in the last few years in helping computers make sense of language,” said Arvind Narayanan, a computer scientist at Princeton University and the paper’s senior author.

   • 2023 May 1, Oliver Whang, “A.I. Is Getting Better at Mind-Reading”, in The New York Times‎^[2], New York, N.Y.: The New York Times Company, →ISSN, →OCLC, archived from the original on 2023-05-17:

     A few years ago, Dr. [Alexander] Huth noticed that particular pieces of these maps — so-called context embeddings, which capture the semantic features, or meanings, of phrases — could be used to predict how the brain lights up in response to language.

embedding

1. present participle and gerund of embed

•   Word embedding on Wikipedia.Wikipedia