Vecteur contextuel compact


Révision datée du 31 décembre 2018 à 15:45 par Pitpitt (discussion | contributions) (Remplacement de texte — « Termes privilégiés » par « Français »)

Domaine

Vocabulary Apprentissage profond

Définition

Français

Anglais

Embedding

An embedding maps an input representation, such as a word or sentence, into a vector. A popular type of embedding are word embeddings such as word2vec or GloVe. We can also embed sentences, paragraphs or images. For example, by mapping images and their textual descriptions into a common embedding space and minimizing the distance between them, we can match labels with images. Embeddings can be learned explicitly, such as in word2vec, or as part of a supervised task, such as Sentiment Analysis. Often, the input layer of a network is initialized with pre-trained embeddings, which are then fine-tuned to the task at hand.