Verified65% confidenceFactExact time
A Bi-Encoder encodes queries and documents independently into vectors and computes relevance via cosine similarity or dot product; document vectors can be pre-computed offline and stored in a vector database.
3
Sources
65%
Confidence
Long-term
Relevance
7/22/2026
First Seen
Sources
Related Claims
Unverified现代Sentence Embedding模型通常采用双塔（Bi-Encoder）结构，查询和文档分别独立编码为向量84% similarUnverifiedBi-Encoder将问题和文档分别独立编码成向量再计算相似度，Cross-Encoder将问题和候选文档拼接后一起输入模型通过注意力机制充分交互82% similarUnverified嵌入模型采用双塔（Bi-encoder）架构，将查询和文档独立编码成向量，然后通过余弦相似度等方式计算距离78% similarUnverifiedRetrieval BERT uses a Bi-Encoder (dual-tower model), where two sentences each generate a vector and similarity is then computed; vectors can be precomputed offline, enabling fast online matching.77% similarUnverifiedA dense dual-encoder consists of two independent neural networks—a query encoder and a document encoder—that map queries and documents into the same vector space.74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/588958API
curl https://kongchang.com/api/v1/knowledge/claims/588958MCP
get_claim(id=588958)