Jump to navigation Jump to search
embedding (plural embeddings)
- The act or process by which one thing is embedded in another.
- (mathematics) A map which maps a subspace (smaller structure) to the whole space (larger structure).
- (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, →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, 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.
- The translations below need to be checked and inserted above into the appropriate translation tables. See instructions at Wiktionary:Entry layout § Translations.