Unverified50% confidenceFactExact time
BERT分类任务中[CLS]标记的最终隐藏状态向量维度为768维（BERT-base）或1024维（BERT-large），被视为整个句子的语义表示
1
Sources
50%
Confidence
Long-term
Relevance
7/13/2026
First Seen
Sources
BERT新增分类类别：增量微调的三种策略与灾难性遗忘解法
Related Claims
UnverifiedBERT分类任务中通常取[CLS]标记对应的隐藏状态向量（维度一般为768或1024）作为句子整体表示，再接一个线性分类头映射到目标类别数84% similarVerifiedSemantically similar texts are also close in distance within vector space, which is the mathematical foundation of vector retrieval.55% similarUnverifiedA token is the basic unit of billing for large models and is essentially the smallest semantic segment after text is split.54% similarUnverifiedBERT模型通过双向编码同时捕捉词语左侧和右侧的完整语境54% similarUnverified语义层描述约4KB即可包含核心业务指标定义、维度层级关系、业务规则和字段别名映射等信息54% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/502973API
curl https://kongchang.com/api/v1/knowledge/claims/502973MCP
get_claim(id=502973)