Aller au contenu
Menu
Français

Cross-Encoder

Model that scores a query and a passage together in one forward pass.

concept Techniques 3 relationships

Aperçu

A cross-encoder concatenates the query and one candidate passage and runs them through the model together, producing a relevance score for that pair. It solves the problem that independent embeddings cannot represent how a specific query relates to a specific passage. It exists as the accurate but expensive half of retrieval: accurate enough to reorder a shortlist, too slow to search a corpus with.

Graphe des technologies

Comment Cross-Encoder se rattache au reste de la pile.

Utilise et dépend de

Utilisé par

Alternatives

Comparaisons

Comparaisons détaillées avec les alternatives ci-dessus.