Cross-Encoder
المُرمِّز التقاطعي
بنية تُمرِّر الاستعلام والمستند معاً كمدخل واحد لمُرمِّز BERT، فتلتقط التفاعلات الدقيقة بينهما. أدق من المُرمِّز الثنائي لكنها أبطأ بكثير لأنها لا تتيح الترميز المسبق.
An architecture that passes query and document together as a single input to a BERT encoder, capturing fine-grained interactions. More accurate than bi-encoders but much slower as it cannot pre-encode documents.
Also translated asالمُرمِّز المتقاطع، نموذج الترميز المشترك
First appears in this corpus in: Okapi at TREC-3 (1994)
Appears in these papers
- Okapi at TREC-31994in the sky ✦
- ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT2020in the sky ✦
- ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT2020in the sky ✦
- Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning2022in the sky ✦
- Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks2019in the sky ✦
- Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks2019in the sky ✦