Перейти к содержимому
Меню
Русский

Cross-Encoder

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

concept Методы 3 relationships

Обзор

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.

Граф технологий

Как Cross-Encoder связана с остальным стеком.

Использует и зависит от

Используется в

Альтернативы

Сравнения

Подробные сопоставления с альтернативами выше.